Predicting Risk Of Malignancy Research Articles

An imaging-based model to predict the malignant potential of intraductal papillary mucinous neoplasm of the pancreas.

To develop and validate imaging-based models for predicting the malignancy risk of intraductal papillary mucinous neoplasm (IPMN). We retrospectively analyzed data from 241 IPMN patients who underwent preoperative CT and MRI for model development. Cyst size, presence and size of the enhancing mural nodule (EMN), main pancreatic duct (MPD) diameter, thickened/enhancing cyst wall, abrupt MPD caliber change with distal atrophy, and lymphadenopathy were assessed. Multiple logistic regression models predicting malignancy risk were created using either continuous (Model C) or dichotomized variables (Model D) using these imaging features. Validation included internal (n = 55) and external (n = 43) datasets. Model performance was assessed using the area under the receiver operating characteristic curve (AUC) and compared with that of the international guideline-based model (Model F). Model C identified age, EMN size, MPD diameter, and lymphadenopathy as independent predictors on CT, and age and presence and size of EMN on MRI. Model D identified age ≥ 68, cyst size ≥ 31 mm, EMN ≥ 6 mm, MPD ≥ 7 mm, and lymphadenopathy as independent predictors on CT, and age ≥ 68, EMN ≥ 4.5 mm, and lymphadenopathy on MRI. Model C (AUC, 0.763-0.899) performed slightly better than Model D (AUC, 0.753-0.912) without statistical significance. No significant difference was observed between Models C and F (AUC, 0.729-0.952). Combining Model C with obstructive jaundice improved performance (AUC, 0.802-0.941) without statistical significance. Our imaging-based models effectively predicted the malignancy risk of IPMNs, comparable to international consensus guidelines. Imaging features are important for predicting the malignant potential of IPMNs. Our imaging-based model may help determine surgical candidacy for patients with IPMNs. Non-invasively determining the malignant potential of intraductal papillary mucinous neoplasms (IPMNs) allows for appropriate treatment decision-making We identified multiple imaging features that are associated with malignant transformation and developed models for this prediction. Our model performs comparably with international consensus guidelines in predicting the malignant potential of IPMNs.

Deep Learning Models for Predicting Malignancy Risk in CT-Detected Pulmonary Nodules: A Systematic Review and Meta-analysis.

There has been growing interest in using artificial intelligence/deep learning (DL) to help diagnose prevalent diseases earlier. In this study we sought to survey the landscape of externally validated DL-based computer-aided diagnostic (CADx) models, and assess their diagnostic performance for predicting the risk of malignancy in computed tomography (CT)-detected pulmonary nodules. An electronic search was performed in four databases (from inception to 10 August 2023). Studies were eligible if they were peer-reviewed experimental or observational articles comparing the diagnostic performance of externally validated DL-based CADx models with models widely used in clinical practice to predict the risk of malignancy. A bivariate random-effect approach for the meta-analysis on the included studies was used. Seventeen studies were included, comprising 8553 participants and 9884 nodules. Pooled analyses showed DL-based CADx models were 11.6% more sensitive than physician judgement alone, and 14.5% more than clinical risk models alone. They had a similar pooled specificity to physician judgement alone [0.77 (95% CI 0.68-0.84) v 0.81 (95% CI 0.71-0.88)], and were 7.4% more specific than clinical risk models alone. They had superior pooled areas under the receiver operating curve (AUC), with relative pooled AUCs of 1.03 (95% CI 1.00-1.07) and 1.10 (95% CI 1.07-1.13) versus physician judgement and clinical risk models alone, respectively. DL-based models are already used in clinical practice in certain settings for nodule management. Our results show their diagnostic performance potentially justifies wider, more routine deployment alongside experienced physician readers to help inform multidisciplinary team decision-making.

Deep learning system for malignancy risk prediction in cystic renal lesions: a multicenter study.

To develop an interactive, non-invasive artificial intelligence (AI) system for malignancy risk prediction in cystic renal lesions (CRLs). In this retrospective, multicenter diagnostic study, we evaluated 715 patients. An interactive geodesic-based 3D segmentation model was created for CRLs segmentation. A CRLs classification model was developed using spatial encoder temporal decoder (SETD) architecture. The classification model combines a 3D-ResNet50 network for extracting spatial features and a gated recurrent unit (GRU) network for decoding temporal features from multi-phase CT images. We assessed the segmentation model using sensitivity (SEN), specificity (SPE), intersection over union (IOU), and dice similarity (Dice) metrics. The classification model's performance was evaluated using the area under the receiver operator characteristic curve (AUC), accuracy score (ACC), and decision curve analysis (DCA). From 2012 to 2023, we included 477 CRLs (median age, 57 [IQR: 48-65]; 173 men) in the training cohort, 226 CRLs (median age, 60 [IQR: 52-69]; 77 men) in the validation cohort, and 239 CRLs (median age, 59 [IQR: 53-69]; 95 men) in the testing cohort (external validation cohort 1, cohort 2, and cohort 3). The segmentation model and SETD classifier exhibited excellent performance in both validation (AUC = 0.973, ACC = 0.916, Dice = 0.847, IOU = 0.743, SEN = 0.840, SPE = 1.000) and testing datasets (AUC = 0.998, ACC = 0.988, Dice = 0.861, IOU = 0.762, SEN = 0.876, SPE = 1.000). The AI system demonstrated excellent benign-malignant discriminatory ability across both validation and testing datasets and illustrated improved clinical decision-making utility. In this era when incidental CRLs are prevalent, this interactive, non-invasive AI system will facilitate accurate diagnosis of CRLs, reducing excessive follow-up and overtreatment. The rising prevalence of CRLs necessitates better malignancy prediction strategies. The AI system demonstrated excellent diagnostic performance in identifying malignant CRL. The AI system illustrated improved clinical decision-making utility.

Validating the Modified McGill Thyroid Nodule Score for Assessment of Preoperative Risk of Pediatric Thyroid Malignancy

ObjectiveThe McGill Thyroid Nodule Score (MTNS) is a preoperative tool used to predict the risk for well-differentiated thyroid cancer in adults. It was developed by a multidisciplinary team using established evidence-based risk factors for thyroid cancer. The modified McGill Thyroid Nodule Score (mMTNS) was developed to predict malignancy risk in children. A pilot study suggested the mMTNS was able to assess malignancy risk in children with indeterminate cytology on fine needle aspiration (FNA). This study seeks to validate these findings. MethodsRetrospective chart review identified subjects who underwent FNA biopsy and subsequent resection. Each patient was assigned a score to compare to final pathology. Statistical analysis was performed with SPSS. All tests were 2-tailed and statistical significance defined p < 0.05. Logistic regression used to determine predictive values of scores. Results46 patients ≤21 years of age underwent resection of a thyroid nodule. Female predominance of 85% (n = 39). 78% (n = 36) of patients had palpable nodule. 65% (n = 30) found to have benign pathology and 35% (n = 16) found to have malignancy. Malignant nodules associated with greater mean mMTNS compared to benign [13.63 vs 7.23]. An mMTNS greater >12 had sensitivity of 86.7%, specificity of 90.3%, positive predictive value of 81.3%, and negative predictive value of 93.3%. ConclusionOur data suggests the mMTNS continues to be a useful adjunct in predicting malignancy risk of pediatric thyroid nodules. An mMTNS >12 has a high risk for malignancy, which can aid in counseling and clinical decision making, particularly when there is indeterminate cytology on FNA. Level of EvidenceIV.

Determining the impact of an artificial intelligence tool on the management of pulmonary nodules detected incidentally on CT (DOLCE) study protocol: a prospective, non-interventional multicentre UK study

IntroductionIn a small percentage of patients, pulmonary nodules found on CT scans are early lung cancers. Lung cancer detected at an early stage has a much better prognosis. The British...

Diagnostic value of American College of Radiology Thyroid Imaging Reporting and Data System combined with elastography in differentiating clinically atypical subacute thyroiditis from papillary thyroid carcinoma: a single retrospective research

BackgroundCommon ultrasound imaging is hard to distinguish thyroid nodules of clinically atypical subacute thyroiditis (CAST) with papillary thyroid carcinoma (PTC). The purpose of this study was to investigate the diagnostic value of real-time elastography combined with American College of Radiology Thyroid Imaging Reporting and Data System (ACR-TIRADS) in differentiating these two lesions.ResultsCentripetal reduction echogenicity was only observed in the CAST nodules, with high specificity (100%) though low sensitivity (23.96%). Echogenic foci yielded good capability for differentiating PTC and CAST, with odds ratio (OR) of 36.572 and AUC of 0.788. Size and ES were independent factors to distinguish the two lesions with OR of 10.709 and 3.697, respectively. The combination of microcalcification, size < 10 mm and ES of 4 showed better AUC (0.885) than echogenic foci alone (p < 0.001). TI-RADS showed high sensitivity (91.23%) with specificity of 30.21% and AUC of 0.607 in predicting malignancy risk of PTC from CAST, while the AUC of ES and the combination of both methods were 0.508 and 0.585, respectively.ConclusionsCentripetal reduction echogenicity, echogenic foci, size and ES may assist in the differential diagnosis of CAST and PTC nodules. ACR TI-RADS is superior to ES and the combination of both methods for distinguishing these two lesions.

Combination of Serum CA 19-9 and Endoscopic Ultrasound Findings Can Predict Malignancy Risk in Patients With Chronic Pancreatitis Presenting With Pancreatic Head Mass: A Proof-of-Concept Study.

Inflammatory head mass of pancreas (IMP) developing in background of chronic pancreatitis (CP) is difficult to distinguish from carcinoma pancreas. We aimed to delineate natural course of IMP and predict their malignancy risk, avoiding unnecessary biopsies. In this retrospective single-center study, clinical records of patients with CP with diagnosed pancreatic head mass were reviewed. Clinical, laboratory, imaging, endoscopic findings, and follow-up details were retrieved from prospectively maintained database. A diagnostic nomogram was developed combining serum cancer antigen 19-9 and endoscopic ultrasound (EUS) findings to predict the risk of malignancy. We identified 107 patients with pancreatic head mass with CP of whom 87 (81.3%) were IMP and 20 (18.7%) were malignant. Patients with IMP were more frequently young males with alcohol-related CP and low CA 19-9 in comparison with those with malignancy (age IMP: 41.3 ± 11.3 vs carcinoma: 49.3 ± 14.5 years [ P = 0.009]; males 89.7% vs 65% [ P = 0.011]; alcoholic etiology: 71.3% vs 20% [ P < 0.001]; median CA 19-9: 25.78 [interquartile range, 7.20-120.60] vs 1034.50 [106.65-7808.25] [ P < 0.001]). A diagnostic nomogram combining CA 19-9 and EUS findings could identify malignancy with an optimism-corrected c-statistic of 0.905, which was better than both CA 19-9 (0.80) and EUS alone (0.826). Patients with IMP had relatively benign disease course with 40.2% biliary obstruction, 20.7% portal venous thrombosis, 14.9% gastric outlet obstruction, and 1-, 3-, and 5-year survival being 97.3%, 92.7%, and 92.0%, respectively. Surgery was required in only 12 patients (13.8%) with IMP. Combination of CA 19-9 and EUS best identifies malignancy risk in patients with IMP, who have otherwise benign course.

Evaluation of American College of Radiology Ovarian-Adnexal Reporting and Data System ultrasound to predict malignancy risk in adnexal lesions.

To validate the diagnostic performance of Ovarian-Adnexal Reporting and Data System (O-RADS) ultrasound for preoperative adnexal lesions in an external center. The secondary aim was to evaluate the performance of a strategy test including O-RADS ultrasound evaluation and subjective assessment of higher malignant risk lesions. One hundred thirty patients with 158 ovarian-adnexal lesions were enrolled in the study. Each lesion was assigned an O-RADS score after real-time ultrasound examination by one experienced radiologist. A second subjective assessment by an expert was performed for O-RADS 4 and O-RADS 5 lesions. The histopathological diagnosis was used as the reference standard. A total of 126 benign and 32 malignant adnexal masses were included in the study. The area under the receiver operating characteristic curve of O-RADS ultrasound was 0.950, with a cutoff value > O-RADS 3. The sensitivity, specificity, and negative and positive predictive values were 100% (95% confidence interval [CI], 0.867-1), 83.3% (95% CI, 0.754-0.892), 60.4% (95% CI, 0.460-0.732), and 100% (95% CI, 0.956-1), respectively. For the strategy test, the sensitivity, specificity, negative and positive predictive values were 100% (95% CI, 0.867-1), 92.1% (95% CI, 0.855-0.959), 76.2% (95% CI, 0.602-0.874), and 100% (95% CI, 0.960-1), respectively. In comparison with O-RADS ultrasound, the specificity and negative predictive value of the strategy test were slightly higher (p < 0.05). Good diagnostic performance of the O-RADS ultrasound in adnexal lesions can be achieved by experienced radiologists in clinical practice. A second subjective assessment of sonographic findings can be applied to O-RADS 4 and 5 lesions.

A Systematic Review and Meta-analysis on Ultrasound Detection of Thyroid Cancer in China

Background: One major drawback of using ultrasound for diagnosing thyroid nodules is its limited ability to distinguish between benign and malignant nodules. In China, the common methods for risk stratification and guiding fine needle aspiration (FNA) in diagnosing thyroid nodules are the Chinese Thyroid Imaging Reports and Data Systems (C-TIRADS) and American College of Radiology-Thyroid Imaging Reporting and Data System (ACR-TIRADS). Objectives: This review seeks to assess the effectiveness of C-TIRADS and ACR-TIRADS in accurately identifying the risk of malignancy in Chinese patients suspected of thyroid cancer. Methods: A detailed search was conducted in PubMed, Google Scholar, Medline, Embase, Web of Science, Cochrane, and China National Knowledge Infrastructure (CNKI) databases from January 2018 to December 2022. The analysis only considered original articles from China reporting the use of C-TIRADS and ACR-TIRADS confirmed by histology and FNA. Results: This review analyzed 26 studies with a total of 23,064 thyroid nodules from 19,114 patients to compare the diagnostic performance of C-TIRADS and ACR-TIRADS in predicting malignancy risk in thyroid nodules. Although the malignancy rates in each risk category were similar between the two systems, the TIRADS showed better diagnostic performance than C-TIRADS in terms of pooled specificity (95.0 % vs. 66.8 % of C-TIRADS). However, the pooled analysis showed that C-TIRADS had a better pooled sensitivity (94.6 % vs. 76.5% of ACR-TIRADS). The diagnostic odds ratio was 1.37 (95 % CI: 0.75-2.51) for ACR-TIRADS and 0.89 (95 % CI: 0.36-2.16) for C-TIRADS. Conclusion: Based on the results, both C-TIRADS and ACR-TIRADS are effective in predicting the risk of malignancy in thyroid nodules with similar overall diagnostic accuracy. The combination of both systems can be beneficial in enhancing accuracy in suspicious or uncertain cases. The long-term experience of the trained radiologists can readily help in concluding the diagnosis. As no single system or combination of systems can provide a 100% accurate prediction of the malignancy of thyroid nodules, the ultimate diagnosis relies on the concluding assessment of experienced radiologists and the medical team.

Application of artificial intelligence in predicting malignancy risk in breast masses on ultrasound.

To evaluate the results obtained with an artificial intelligence-based software for predicting the risk of malignancy in breast masses from ultrasound images. This was a retrospective, single-center study evaluating 555 breast masses submitted to percutaneous biopsy at a cancer referral center. Ultrasonographic findings were classified in accordance with the BI-RADS lexicon. The images were analyzed by using Koios DS Breast software and classified as benign, probably benign, low to intermediate suspicion, high suspicion, or probably malignant. The histological classification was considered the reference standard. The mean age of the patients was 51 years, and the mean mass size was 16 mm. The radiologist evaluation had a sensitivity and specificity of 99.1% and 34.0%, respectively, compared with 98.2% and 39.0%, respectively, for the software evaluation. The positive predictive value for malignancy for the BI-RADS categories was similar between the radiologist and software evaluations. Two false-negative results were identified in the radiologist evaluation, the masses in question being classified as suspicious by the software, whereas four false-negative results were identified in the software evaluation, the masses in question being classified as suspicious by the radiologist. In our sample, the performance of artificial intelligence-based software was comparable to that of a radiologist.

Correlation of ACR TI-RADS and Patient Outcomes in a Real-World Cohort Presenting for Thyroid Ultrasonography.

The American College of Radiology Thyroid Image Reporting and Data System (ACR TI-RADS) was developed to predict malignancy risk in thyroid nodules using ultrasound features. TI-RADS was derived from a database of patients already selected for fine-needle aspiration (FNA), raising uncertainty about applicability to unselected patients. We aimed to assess the effect of ACR TI-RADS reporting in unselected patients presenting for thyroid ultrasound in a real-world setting. Records for all patients presenting for thyroid ultrasonography in Canterbury, New Zealand, were reviewed across two 18-month periods, prior to and after implementation of TI-RADS reporting. Patient outcomes were compared between the 2 periods. Malignancy rates were calculated for nodules 10 mm or larger with a definitive FNA or histology result. A total of 1210 nodules were identified in 582 patients prior to implementation of TI-RADS; 1253 nodules were identified in 625 patients after implementation of TI-RADS. TI-RADS category was associated with malignancy rate (0% in TR1 and TR2, 3% in TR3, 5% in TR4, 12% in TR5; P = .02); however, 63% of nodules were graded TR3 or TR4, for which malignancy rate did not meaningfully differ from baseline risk. After implementation of TI-RADS there was a small reduction in the proportion of patients proceeding to FNA (49% vs 60%; P < .01) or surgery (14% vs 18%; P < .05), with no difference in cancer diagnoses (3% vs 4%, not significant). TI-RADS category is associated with malignancy rate and may alter clinical decision-making in a minority of patients; however, it is nondiscriminatory in the majority of nodules. In this study of unselected patients, nodules classified as TR5 and thus considered "highly suspicious" for cancer had only a modest risk of malignancy.

Utility of Brock model for risk stratification in patients with high-risk pulmonary nodules: A single center study.

e18824 Background: Owing to the widespread implementation of low-dose CT screening (LDCT), an increasing number of pulmonary nodules are being identified. Per LDCT lung cancer screening protocol, radiologists assign Lung-RADS (LR) scores ranging from 1-4 with L1-2 being at low risk and L3-4 being at intermediate to high risk of malignancy. The Brock model derived from the Pan-Canadian Early Detection of Lung Cancer screening study is a mathematical model that incorporates both clinical (age, sex, family history of lung cancer) and radiological (emphysema, nodule size, location of nodule in the upper lobe, nodule type, nodule count and spiculation) factors to predict the risk of lung cancer, but is not commonly used in the United States. The goal of our study was to estimate whether a higher Brock score can be used to further stratify malignancy potential in patients with LR≥3. Methods: We performed a retrospective analysis at Mercy Catholic Medical Center, where we reviewed LDCT findings of 1090 patients, performed between 1/1/2018 - 6/30/2021 and identified 82 patients with LR≥3. Brock Model was used to calculate the malignancy probability of these pulmonary nodules. All patients were followed until biopsy, resolution of nodule or stability on follow-up imaging. In patients with multiple pulmonary nodules, probability was estimated for the largest nodule. An analysis of area under the receiver operating characteristic curve (AUC) was performed to evaluate efficiency of Brock model in our study population (using GraphPad Prism). We used the British Thoracic Society’s suggested threshold of 10% malignancy risk. Results: 82 patients (43 females and 39 males) were found to have pulmonary nodules with LR≥3. Among these, 10 patients were lost to follow-up and excluded from this study. Out of the 38 patients with LR 4, 16 patients had biopsy-proven lung cancer, 22 patients were found to have benign nodules. Among 34 patients with LR 3, only 3 were found to have lung cancer on follow-up. The mean calculated malignancy risk percentage was 6.69% for benign nodules (n = 51), but 27.14% for malignant nodules (n = 18). The calculated AUC in our study population was 0.85 (95%, CI 0.75-0.95, p &lt; 0.0001). At 10% threshold, sensitivity and specificity were 78.95% and 83.02%, respectively. Conclusions: Based on our data, this model can be used to further assess risk of lung cancer in patients with intermediate to high-risk lung nodules (LR≥3). Similar to the use of Tyrer-Cuzick and Gail models in assessing risk of breast cancer, we may be able to use the Brock Model in predicting malignancy risk of lung nodules. However, a larger study is needed to estimate specific cut-offs. This can potentially lower the need for biopsies in lower risk groups and warrant more aggressive work-up and early diagnosis in higher risk populations.

Deep learning and radiomic feature-based blending ensemble classifier for malignancy risk prediction in cystic renal lesions

BackgroundThe rising prevalence of cystic renal lesions (CRLs) detected by computed tomography necessitates better identification of the malignant cystic renal neoplasms since a significant majority of CRLs are benign renal cysts. Using arterial phase CT scans combined with pathology diagnosis results, a fusion feature-based blending ensemble machine learning model was created to identify malignant renal neoplasms from cystic renal lesions (CRLs). Histopathology results were adopted as diagnosis standard. Pretrained 3D-ResNet50 network was selected for non-handcrafted features extraction and pyradiomics toolbox was selected for handcrafted features extraction. Tenfold cross validated least absolute shrinkage and selection operator regression methods were selected to identify the most discriminative candidate features in the development cohort. Feature’s reproducibility was evaluated by intra-class correlation coefficients and inter-class correlation coefficients. Pearson correlation coefficients for normal distribution and Spearman's rank correlation coefficients for non-normal distribution were utilized to remove redundant features. After that, a blending ensemble machine learning model were developed in training cohort. Area under the receiver operator characteristic curve (AUC), accuracy score (ACC), and decision curve analysis (DCA) were employed to evaluate the performance of the final model in testing cohort.ResultsThe fusion feature-based machine learning algorithm demonstrated excellent diagnostic performance in external validation dataset (AUC = 0.934, ACC = 0.905). Net benefits presented by DCA are higher than Bosniak-2019 version classification for stratifying patients with CRL to the appropriate surgery procedure.ConclusionsFusion feature-based classifier accurately distinguished malignant and benign CRLs which outperformed the Bosniak-2019 version classification and illustrated improved clinical decision-making utility.

American Thyroid Association and Thyroid Imaging Reporting and Data System developed by the American College of Radiology: which one is better at predicting malignancy risk?

The aim of this study was to compare the capacity of American Thyroid Association and Thyroid Imaging Reporting and Data System developed by the American College of Radiology in predicting malignancy risk of thyroid nodules and to verify which one is better at avoiding unnecessary fine needle aspiration. This was a cross-sectional study with 565 thyroid nodules, followed at a tertiary care hospital, in an iodine-replete area. Those were classified as American Thyroid Association and Thyroid Imaging Reporting and Data System developed by the American College of Radiology systems and stratified according to the Bethesda classification of fine needle aspiration. The values of sensibility, specificity, positive predictive value, and negative predictive value accuracy were calculated. Also, the percentage of unnecessary biopsies was presented. The mean age of the individuals was 58.2±13.5 [26-90] years for benign nodules and 41.7±15.6 [23-66] years for malignant nodules (p=0.002). Regarding gender, 92.6% (n=150) of the individuals with benign nodules and 85.7% (n=06) with malignant nodules were females (p=0.601). For American Thyroid Association, 90.9% of sensibility, 51.4% of specificity, 52.6% of accuracy, 10.2% of positive predictive value, and 98.9% of negative predictive value were found. For Thyroid Imaging Reporting and Data System developed by the American College of Radiology, 90.9% of sensibility, 49.7% of specificity, 52.1% of accuracy, 9.9% of positive predictive value, and 98.9% of negative predictive value were found. .Notably, 12.3% of unnecessary fine needle aspiration were found in American Thyroid Association and 44.4% were found in Thyroid Imaging Reporting and Data System developed by the American College of Radiology. Both Thyroid Imaging Reporting and Data System developed by the American College of Radiology and American Thyroid Association are able to predict the malignancy risk of thyroid nodules. Thyroid Imaging Reporting and Data System developed by the American College of Radiology was better at avoiding unnecessary fine needle aspiration.

Accuracy of fine‐needle aspiration cytopathology to differentiate malignant and benign thyroid nodules with ≥4 cm diameter: A retrospective study

Thyroid nodules (TN) are commonly present in the general population and are usually pathologically benign. An initial diagnosis with fine-needle aspiration (FNA) cytopathology could help clinical decision-making with fewer complications. As the previous studies suggest surgical procedures for >4cm TNs, we aimed to investigate the accuracy of preoperative FNA cytology to predict malignancy risk in these nodules in a sample of the Iranian population. Patients with ≥4cm TNs who had preoperative FNA cytology, underwent nodulectomy and had a histopathological report were included. Each patient's preoperative demographic, ultrasonographic, and cytology data were gathered. After surgery, resected samples were assessed pathologically and diagnosed as benign or malignant. Finally, data were analyzed to evaluate the presurgical accuracy of the FNA cytology. We identified 41 (51.25%) patients with malignant legions among our study population (N= 80). The pathology reports were indeterminate in 3 patients with follicular neoplasm. Bethesda scores were substantially higher in patients with malignancy. The sensitivity, specificity, and false-negative rate of FNA cytology reports using the Bethesda system were 73.7%, 74.2%, and 26.3%, respectively. There was no association between malignancy and TNs' size, neither their volume nor their highest diameter. FNA cytology is not as sensitive and specific in nodules>4cm as in smaller ones. However, it can still be used alongside other diagnostic procedures in malignancy screening. Clinicians should make more complex decisions considering various influential factors to avoid missing malignant lesions and reduce diverse probable complications of highly invasive diagnostic surgery. Further prospective research on >4cm TNs and their multiple features' association with malignancy is required for more precise judgment.

Vet-OncoNet: Malignancy Analysis of Neoplasms in Dogs and Cats.

Simple SummaryAn overview analysis of tumors in dogs and cats, dividing them into malignant and benign, may provide previously unknown information about the biological behavior of tumors in these species and may serve many veterinarians as a support for clinical decision making. Based on a sample of 16,272 cancer records, including 3266 cats and 13,006 dogs, the analysis found that cats have a fourfold risk of malignant tumors, as in some topographies. Sex appears to play a role in the malignancy only in dogs. Some dog breeds (Pit bull and Boxer) have a higher risk of malignant tumors as opposed to Shih tzu and Yorkshire terrier. District of residence was not relevant in predicting malignancy risk. Most importantly, the risk of malignant tumors increases by 20% every three years.Analysis of canine and feline tumor malignancy data can help clinicians identify high-risk patients and make more accurate decisions. Based on a sample of 16,272 cancer records, including 3266 cats and 13,006 dogs, collected from January 2019 to December 2021 in the Vet-OncoNet Network database, this study aimed to compare the tumor malignancy profile between cats and dogs, considering animal-related factors (sex, age, and breed), topography, and geographic location using a mixed-effects logistic regression model. Cats had a higher proportion of malignant tumors (78.7%) than dogs (46.2%), and the malignancy profile was very different regarding tumors’ topographies. The mean age of malignant tumors occurred eight months later than benign ones (9.1, SD = 3.4; 9.8, SD = 3.2), in general. Species (OR = 3.96, 95%CI 3.57: 4.39) and topography (MOR = 4.10) were the two most important determinants of malignancy risk. Female dogs had a higher risk than male dogs (OR = 1.19, 95%CI 1.08: 1.31), which does not appear to be the case in cats (OR = 0.98, 95%CI 0.77: 1.23). Breed contributed significantly to differences in malignancy risk in dogs (MOR = 1.56), particularly in pit bulls and boxers. District of residence was not so relevant in predicting malignancy risk (MOR = 1.14). In both species, the risk of malignancy increased by approximately 20% every three years. It could be hypothesized that species differences in genetic structure may contribute to tumor malignancy.

Improving malignancy risk prediction of indeterminate pulmonary nodules with imaging features and biomarkers

BackgroundNon-invasive biomarkers are needed to improve management of indeterminate pulmonary nodules (IPNs) suspicious for lung cancer. MethodsProtein biomarkers were quantified in serum samples from patients with 6–30 mm IPNs (n = 338). A previously derived and validated radiomic score based upon nodule shape, size, and texture was calculated from features derived from CT scans. Lung cancer prediction models incorporating biomarkers, radiomics, and clinical factors were developed. Diagnostic performance was compared to the current standard of risk estimation (Mayo). IPN risk reclassification was determined using bias-corrected clinical net reclassification index. ResultsAge, radiomic score, CYFRA 21-1, and CEA were identified as the strongest predictors of cancer. These models provided greater diagnostic accuracy compared to Mayo with AUCs of 0.76 (95 % CI 0.70–0.81) using logistic regression and 0.73 (0.67–0.79) using random forest methods. Random forest and logistic regression models demonstrated improved risk reclassification with median cNRI of 0.21 (Q1 0.20, Q3 0.23) and 0.21 (0.19, 0.23) compared to Mayo for malignancy. ConclusionsA combined biomarker, radiomic, and clinical risk factor model provided greater diagnostic accuracy of IPNs than Mayo. This model demonstrated a strong ability to reclassify malignant IPNs. Integrating a combined approach into the current diagnostic algorithm for IPNs could improve nodule management.

Prediction of malignancy in main duct or mixed-type intraductal papillary mucinous neoplasms of the pancreas.

Surgical indications of main duct-involved intraductal papillary mucinous neoplasm (IPMN), especially for main pancreatic duct (MPD) of 5-9 mm, remain controversial. We aimed to predict malignancy risk of main duct-involved IPMN. Total 258 patients with main duct-involved IPMN between 2000 and 2017 in our institute were retrospectively analyzed. Main duct IPMN was classified into segmental and diffuse-type by dilated MPD pattern. Clinicopathologic features and predictive factors for malignancy were analyzed. Among 258 patients, 47 and 211 had pure main duct (segmental: 27, diffuse type: 20) and mixed type, respectively. Malignant IPMN presented higher in main duct type (66.0%) compared to mixed type (46.9%). The diffuse type (72.2%) had more invasive carcinoma than the segmental type (40.7%). Invasive IPMN risk increased proportionally to the MPD diameter (5 ≤ MPD <10 mm vs 10 ≤ MPD < 15 mm vs MPD ≥ 15 mm; 23.4% vs 40.0% vs 48.6%). Symptoms, elevated serum carbohydrate antigen, MPD ≥10 mm, mural nodule, thickened wall, and distal atrophy were independent predictive factors for malignancy. Patients with MPD of 5-9 mm with at least one predictive factor had 35.0% of malignancy risk. The invasive IPMN risk was different according to the dilated main duct pattern. Patients with main duct type, diffuse type, MPD ≥10 mm, and MPD 5-9 mm with at least one predictive factor should be candidates for immediate surgery.

Comprehensive quantitative malignant risk prediction of pure grouped amorphous calcifications: clinico-mammographic nomogram.

Pure grouped amorphous calcifications are classified as Breast Imaging Reporting and Data System (BI-RADS) category 4B suspicious calcifications and recommended for biopsy. However, the biopsies often reveal benign findings, especially in screening mammograms (92.4-97.2%). Mammograms of 699 pure grouped amorphous calcifications with final pathological results were analyzed in this retrospective study. The maximum span (MS) of the group of calcifications and the MS of the parallel/vertical direction of the mammary duct (MPS/MVS) were measured, and the MPS to MVS ratio was calculated. Based on the MS and ratio, 2 prediction nomograms with other clinic-mammographic features were developed. The discrimination performance of the models was assessed and compared by the area under the receiver operating characteristic curve (AUC). Scatterplots were created to determine the cutoff values with fewer misdiagnoses of malignant calcifications and fewer false positives. Ultimately, 2 prediction models were successfully developed based on the 4 risk factors of age, purpose of the mammogram, whether multiple or single calcifications, and the MS [odds ratio (OR) =1.06, P=0.02]/ratio (OR =6.05, P<0.001). Both models had good discrimination. The ratio model performed better than the MS model in the training cohort (AUC of 0.875 and 0.834, respectively, P=0.003) and validation cohort (AUC 0.908 and 0.867, respectively, P=0.047). For the group with probably benign calcifications (as detected by the ratio nomogram), the malignancy rates were 2.7% [95% confidence interval (CI): 1.00% to 6.53%] and 1.19% (95% CI: 0.06% to 7.37%) in the training and validation cohorts, respectively, and 44.12% and 47.70% of benign biopsies were detected in the training and validation cohorts, respectively. The clinico-mammographic quantitative malignancy risk prediction nomogram showed favorable discrimination and calibration performance. The ratio model showed better diagnostic efficiency than the MS model, and identified >40% of benign biopsies.

A Computed Tomography Nomogram for Assessing the Malignancy Risk of Focal Liver Lesions in Patients With Cirrhosis: A Preliminary Study.

PurposeThe detection and characterization of focal liver lesions (FLLs) in patients with cirrhosis is challenging. Accurate information about FLLs is key to their management, which can range from conservative methods to surgical excision. We sought to develop a nomogram that incorporates clinical risk factors, blood indicators, and enhanced computed tomography (CT) imaging findings to predict the nature of FLLs in cirrhotic livers.MethodA total of 348 surgically confirmed FLLs were included. CT findings and clinical data were assessed. All factors with P < 0.05 in univariate analysis were included in multivariate analysis. ROC analysis was performed, and a nomogram was constructed based on the multivariate logistic regression analysis results.ResultsThe FLLs were either benign (n = 79) or malignant (n = 269). Logistic regression evaluated independent factors that positively affected malignancy. AFP (OR = 10.547), arterial phase hyperenhancement (APHE) (OR = 740.876), washout (OR = 0.028), satellite lesions (OR = 15.164), ascites (OR = 156.241), and nodule-in-nodule architecture (OR =27.401) were independent predictors of malignancy. The combined predictors had excellent performance in differentiating benign and malignant lesions, with an AUC of 0.959, a sensitivity of 95.24%, and a specificity of 87.5% in the training cohort and AUC of 0.981, sensitivity of 94.74%, and specificity of 93.33% in the test cohort. The C-index was 96.80%, and calibration curves showed good agreement between the nomogram predictions and the actual data.ConclusionsThe nomogram showed excellent discrimination and calibration for malignancy risk prediction, and it may aid in making FLLs treatment decisions.