Tumor Images Research Articles

LW-MorphCNN: A lightweight morphological attention-based subtype classification network for lung cancer

Abstract Lung cancer is generally considered one of the most deadly cancers globally. If it can be identified early and diagnosed correctly, the survival probability of patients can be significantly improved. In this process, histopathological examination is a commonly used method for diagnosing and detecting lung cancer. It is crucial to accurately identify lung cancer subtypes from histopathological images, as this helps doctors formulate effective treatment plans. However, the visual inspection in histopathological diagnosis requires a large amount of time and also depends on the subjective perception of clinicians. Therefore, this paper proposes a lightweight lung cancer subtype classification network based on morphological attention (LW-MorphCNN), which is used to automatically classify the histopathological images of benign lung tumors, ADC (adenocarcinoma), and SCC (squamous cell carcinoma) provided in the public dataset LC25000 (Lung and Colon). This paper takes histopathological images as input and conducts a comparative analysis with classic networks such as VGG16, VGG19, DenseNet121, and ResNet50, as well as existing classification methods proposed in the same work. The network proposed in this paper is superior to other networks in terms of parameter quantity and performance, with an accuracy rate and F1 - score reaching 99.47\% and 99.44\% respectively. Clinicians can install the provided LW-MorphCNN in the hospital to confirm the diagnosis results.

Source free domain adaptation for kidney and tumor image segmentation with wavelet style mining

Kidney cancer is a serious malignant disease, and early diagnosis along with precise segmentation are crucial for effective treatment. However, due to the scarcity of labelled medical image data, the development of the intelligent diagnosis of kidney cancer is restricted. To address this challenge, we propose a novel unsupervised domain adaptation (UDA) framework specifically designed for kidney and tumor CT image segmentation. Our framework consists of a generation phase and an adaptation phase. In the generation phase, we employ a wavelet-based style mining generator to create class-specific source-like images, facilitating domain alignment. In the adaptation phase, we introduce contrastive domain extraction and compact-aware domain consistency modules, enhancing feature-level and output-level adaptability through data augmentation techniques. Experimental results demonstrate that our method performs better in kidney and tumor segmentation tasks, exhibiting higher accuracy and generalization capability than state-of-the-art domain adaptation methods. This indicates that our approach has significant advantages in medical image segmentation for kidneys and tumors.

A New Tool for Extracting Static and Dynamic Parameters from [18F]F-DOPA PET/CT in Pediatric Gliomas

Background/Objectives: PET imaging with [18F]F-DOPA has demonstrated high potential for the evaluation and management of pediatric brain gliomas. Manual extraction of PET parameters is time-consuming, lacks reproducibility, and varies with operator experience. Methods: In this study, we tested whether a semi-automated image processing framework could overcome these limitations. Pediatric patients with available static and/or dynamic [18F]F-DOPA PET studies were evaluated retrospectively. We developed a Python software to automate clinical index calculations, including preprocessing to delineate tumor volumes from structural MRI, accounting for lesions with low [18F]F-DOPA uptake. A total of 73 subjects with treatment-naïve low- and high-grade gliomas, who underwent brain MRI within two weeks of [18F]F-DOPA PET, were included and analyzed. Static analysis was conducted on all subjects, while dynamic analysis was performed on 32 patients. Results: For 68 subjects, the Intraclass Correlation Coefficient for T/S between manual and ground truth segmentation was 0.91. Using our tool, ICC improved to 0.94. Our method demonstrated good reproducibility in extracting static tumor-to-striatum ratio (p = 0.357); however, significant differences were observed in tumor slope (p < 0.05). No significant differences were found in time-to-peak (p = 0.167) and striatum slope (p = 0.36). Conclusions: Our framework aids in analyzing [18F]F-DOPA PET images of pediatric brain tumors by automating clinical score extraction, simplifying segmentation and Time Activity Curve extraction, reducing user variability, and enhancing reproducibility.

Metal-Organic Nanomaterials for Tumor Metabolic Blockade and Image to Increase Tumor Therapy.

The abnormal energy metabolism level of a tumor reduces the efficiency of chemotherapy. Metal-organic nanomaterials (MONs) with high drug loading efficiency, easy processes of synthesis, and controlled drug release have shown great potential in metabolic blocking and enhancement of tumor therapy. These metal-organic nanomedicines have been reported to modulate glycolysis or oxidative phosphorylation to provide monotherapy or combined therapies in tumorous treatments. In addition, the encapsulation or coordination of fluorescent dyes into MONs endowed them with the imaging ability of tumor metabolism. Herein, this Perspective summarizes the progress of MONs as therapeutic agents or imaging probes for application during tumor metabolic blocking or imaging, providing solid inspiration for biomedical applications of effective biomaterials. In addition, the current drawbacks of MONs for further biological applications in the future were discussed, giving stimulation of innovation and development in biomedical applications of MONs.

Retracted] SET and MYND domain‑containing protein 3 is overexpressed in human glioma and contributes to tumorigenicity.

Following the publication of this paper, it was drawn to the Editor's attention by a concerned reader that certain of the colony formation assay data featured in Fig. 4A and C on p. 2726, tumor images in Fig. 6A on p. 2727, and western blotting data shown in Fig. 7A on p. 2728 were strikingly similar to data that had appeared in other articles written by different authors at different research institutes, which had already been published before this article was received at Oncology Reports. Owing to the fact that the abovementioned data had already been published prior to the receipt of this article at Oncology Reports, the Editor has decided that this paper should be retracted from the Journal. The authors were asked for an explanation to account for these concerns, but the Editorial Office did not receive a reply. The Editor apologizes to the readership for any inconvenience caused. [Oncology Reports 34: 2722‑2730, 2015; DOI: 10.3892/or.2015.4239].

Detection and classification on MRI images of brain tumor using YOLO NAS deep learning model

If a brain tumor is not properly diagnosed, it might result in fatal consequences and major health issues. As a result, a key component of diagnosis is the early identification of brain tumors and the precise categorization of brain tumor types. This research work focusses on detection and classification such as pituitary, meningioma, glioma, and non-tumorous tumors from brain tumor MRI image using YOLO NAS model. Advances in deep learning have led to an increasing awareness of computer-aided diagnosis technology. To improve classification performance, the input data set is acquired from the REMBRANDT repository using the Digital Database of Brain Tumor Magnetic Resonance Images. The primary phases of this task include segmentation, classification, and pre-processing. The researcher preprocessed the RGB image to exclude any undesired spots before locating the ROI. For each brain tumor image, we used the hybrid anisotropic diffusion filtering (HADF) technique to remove noise. The Encoder-Decoder Network (En–DeNet), which uses a deep neural network based on U-Net as the encoder and a pre-trained EfficientNet as the decoder, is then used to segment the MRI images. A proposed model was developed using a deep learning-based YOLO NAS technique to identify brain cancers from MRI images such as meningioma tumors, non-tumor, glioma tumors, and pituitary tumors. The suggested model's classification performance is weighed based on parameters such as precision, F1-score, sensitivity, accuracy, and specificity. The proposed fusion method YOLO NAS has improved classification results of accuracy (AC = 0.997%), specificity (SP = 0.985%), precision (PR = 0.982%), F1-score (F1 = 0.992%), and sensitivity (SE = 0.985%) using 2570 MRI data for training and 630 data for testing and validation of brain tumor cases. The results show that the brain tumor type classification system based on the proposed YOLO NAS technique works better than the DNN, PDCNN, DenseNet-161, and DCNN-SGD model classifiers.

Retracted] LncRNA TTN‑AS1 promotes endometrial cancer by sponging miR‑376a‑3p.

Following the publication of this paper, it was drawn to the Editor's attention by a concerned reader that certain of the Transwell cell migration and invasion assay data in Fig. 2E and F and 4E and F, tumor images in Fig. 7B and western blotting data shown in Fig. 4D had already appeared in previously published articles written by different authors at different research institutes (a few of which have been retracted). Owing to the fact that the contentious data in the above article had already been published prior to its submission to Oncology Reports, the Editor has decided that this paper should be retracted from the Journal. The authors were asked for an explanation to account for these concerns, but the Editorial Office did not receive a reply. The Editor apologizes to the readership for any inconvenience caused. [Oncology Reports 44: 1343‑1354, 2020; DOI: 10.3892/or.2020.7691].

Contrast-Enhanced Ultrasound-Based Radiomics for the Prediction of Axillary Lymph Nodes Status in Breast Cancer.

Breast cancer is the leading cause of cancer-related deaths in the female population. Axillary lymph nodes (ALN) are a group of the most common metastatic sites of breast cancer. Timely assessment of ALN status is of paramount clinical importance for medical decision making. To utilize contrast-enhanced ultrasound (CEUS)-based radiomics models for noninvasive pretreatment prediction of ALN status. Clinical data and pretreatment CEUS images of primary breast tumors were retrospectively studied to build radiomics signatures for pretreatment prediction of nodal status between May 2015 and July 2021. The cases were divided into the training cohorts and test cohorts in a 9:1 ratio. The mRMR approach and stepwise forward logistic regression technique were used for feature selection, followed by the multivariate logistic regression technique for building radiomics signatures in the training cohort. The confusion matrix and receiver operating characteristic (ROC) analysis were used for accessing the prediction efficacy of the radiomics models. The radiomics models, which consist of six features, achieved predictive accuracy with the area under the ROC curve (AUC) of 0.713 in the test set for predicting lymph node metastasis. The CEUS-based radiomics is promising to be developed as a reliable noninvasive tool for predicting ALN status.

Robust brain MRI image classification with SIBOW-SVM

Primary Central Nervous System tumors in the brain are among the most aggressive diseases affecting humans. Early detection and classification of brain tumor types, whether benign or malignant, glial or non-glial, is critical for cancer prevention and treatment, ultimately improving human life expectancy. Magnetic Resonance Imaging (MRI) is the most effective technique for brain tumor detection, generating comprehensive brain scans. However, human examination can be error-prone and inefficient due to the complexity, size, and location variability of brain tumors. Recently, automated classification techniques using machine learning methods, such as Convolutional Neural Networks (CNNs), have demonstrated significantly higher accuracy than manual screening. However, deep learning-based image classification methods, including CNNs, face challenges in estimating class probabilities without proper model calibration (Guo et al., 2017; Minderer et al., 2021). In this paper, we propose a novel brain tumor image classification method called SIBOW-SVM, which integrates the Bag-of-Features model with SIFT feature extraction and weighted Support Vector Machines. This new approach can effectively extract hidden image features, enabling differentiation of various tumor types, provide accurate label predictions, and estimate probabilities of images belonging to each class, offering high-confidence classification decisions. We have also developed scalable and parallelable algorithms to facilitate the practical implementation of SIBOW-SVM for massive image datasets. To benchmark our method, we apply SIBOW-SVM to a public dataset of brain tumor MRI images containing four classes: glioma, meningioma, pituitary, and normal. Our results demonstrate that the new method outperforms state-of-the-art techniques, including CNNs, in terms of uncertianty quantification, classification accuracy, computational efficiency, and data robustness.

Lightweight MRI Brain Tumor Segmentation Enhanced by Hierarchical Feature Fusion.

Existing methods for MRI brain tumor segmentation often suffer from excessive model parameters and suboptimal performance in delineating tumor boundaries. For this issue, a lightweight MRI brain tumor segmentation method, enhanced by hierarchical feature fusion (EHFF), is proposed. This method reduces model parameters while improving segmentation performance by integrating hierarchical features. Initially, a fine-grained feature adjustment network is crafted and guided by global contextual information, leading to the establishment of an adaptive feature learning (AFL) module. This module captures the global features of MRI brain tumor images through macro perception and micro focus, adjusting spatial granularity to enhance feature details and reduce computational complexity. Subsequently, a hierarchical feature weighting (HFW) module is constructed. This module extracts multi-scale refined features through multi-level weighting, enhancing the detailed features of spatial positions and alleviating the lack of attention to local position details in macro perception. Finally, a hierarchical feature retention (HFR) module is designed as a supplementary decoder. This module retains, up-samples, and fuses feature maps from each layer, thereby achieving better detail preservation and reconstruction. Experimental results on the BraTS 2021 dataset demonstrate that the proposed method surpasses existing methods. Dice similarity coefficients (DSC) for the three semantic categories ET, TC, and WT are 88.57%, 91.53%, and 93.09%, respectively.

A Bis‐Boron Amino Acid for Positron Emission Tomography and Boron Neutron Capture Therapy

Trifluoroborate boronophenylalanine (BBPA) is a boron amino acid analog of 4‑boronophenylalanine (BPA) but with a trifluoroborate group (‐BF3‐) instead of a carboxyl group (‐COOH). Clinical studies have shown that 18F‐labeled BBPA ([18F]BBPA) can produce high‐contrast tumor images in positron emission tomography (PET). Beyond PET imaging, BBPA is a theranostic agent for boron neutron capture therapy (BNCT). Because BBPA possesses an identical chemical structure to BNCT and PET, it can potentially predict the boron concentration for BNCT using [18F]BBPA‐PET. The synthesis of BBPA was achieved by selectively fluorinating the α‐aminoborate compound, taking advantage of the varying rates of solvolysis of the B‐F bond. The study showcased the high‐contrast [18F]BBPA‐PET imaging in various tumor models, highlighting its broad applicability for both [18F]BBPA‐PET and BBPA‐BNCT. [18F]BBPA‐PET tumor uptake remains consistent across various doses, including those used in BNCT. This enables accurate estimation of the boron concentration in tumors using [18F]BBPA‐PET. With its dual boron structure, BBPA increases boron concentration in tumor cells and tumor tissues compared to BPA. Thus, less boron carrier is needed. This study introduces a new theranostic boron carrier that enhances boron accumulation in tumors, predicts boron concentration, and enhances the accuracy and effectiveness of BNCT.

CAPSULE NETWORK FOR BRAIN TUMORS SEGMENTATION IN MRI IMAGES

Glioma is an abnormal, irregularly shaped cell growth in the brain. Diagnosing glioma often relies on magnetic resonance imaging (MRI), which requires precise segmentation of the tumor for effective analysis. Convolutional Neural Networks (CNN), such as U-Net, is widely used in medical image processing, particularly for image segmentation tasks. However, CNNs have the limitation in effectively learning spatial relationships within images. To address this, Capsule Networks (CapsNet) is introduced, utilizing capsule dynamic routing to better capture spatial hierarchies. This paper aims to investigate the performance of SegCaps, a segmentation model based on Capsule Networks, for brain glioma segmentation in MRI images, compared to the CNN-based U-Net model. Both models were tested on the BraTS2018 glioma dataset, which includes 374 MRI images of brain tumors across four modalities (T1, T1c, T2, FLAIR). The performance of SegCaps and U-Net was evaluated using two key segmentation metrics: Dice coefficient and Jaccard index. The results show that SegCaps outperformed U-Net with a Dice coefficient of 87.96% compared to U-Nets 85.56%, demonstrating a 2.4% improvement. Additionally, SegCaps required fewer parameters than the U-Net model, highlighting its efficiency. In conclusion, SegCaps can be considered as a promising alternative for glioma segmentation in MRI images. Future work could focus on refining the SegCaps model to enhance its performance while reducing computational costs.

MODIFIED VGG16 FOR ACCURATE BRAIN TUMOR DETECTION IN MRI IMAGERY

Brain tumors are one of the most severe medical conditions that require immediate attention and treatment. The early detection of brain tumors is of utmost importance, as it can significantly improve the chances of successful treatment outcomes and increase the patient's quality of life. This study proposes a novel methodology for the early detection of brain tumors in magnetic resonance imaging (MRI) images using a modified VGG16 neural network architecture. The dataset comprises both tumor and non-tumor MRI images collected from Kaggle and has preprocessing techniques applied to optimize the model's performance. The proposed approach delivers an impressive accuracy rate of 99.08%, demonstrating its efficacy in precise brain tumor detection. This new methodology is expected to aid doctors in accurate diagnosis and treatment planning, thereby helping to save more lives and improve the quality of life of patients suffering from brain tumors.

A Bis-Boron Amino Acid for Positron Emission Tomography and Boron Neutron Capture Therapy.

Trifluoroborate boronophenylalanine (BBPA) is a boron amino acid analog of 4‑boronophenylalanine (BPA) but with a trifluoroborate group (-BF3-) instead of a carboxyl group (-COOH). Clinical studies have shown that 18F-labeled BBPA ([18F]BBPA) can produce high-contrast tumor images in positron emission tomography (PET). Beyond PET imaging, BBPA is a theranostic agent for boron neutron capture therapy (BNCT). Because BBPA possesses an identical chemical structure to BNCT and PET, it can potentially predict the boron concentration for BNCT using [18F]BBPA-PET. The synthesis of BBPA was achieved by selectively fluorinating the α-aminoborate compound, taking advantage of the varying rates of solvolysis of the B-F bond. The study showcased the high-contrast [18F]BBPA-PET imaging in various tumor models, highlighting its broad applicability for both [18F]BBPA-PET and BBPA-BNCT. [18F]BBPA-PET tumor uptake remains consistent across various doses, including those used in BNCT. This enables accurate estimation of the boron concentration in tumors using [18F]BBPA-PET. With its dual boron structure, BBPA increases boron concentration in tumor cells and tumor tissues compared to BPA. Thus, less boron carrier is needed. This study introduces a new theranostic boron carrier that enhances boron accumulation in tumors, predicts boron concentration, and enhances the accuracy and effectiveness of BNCT.

Improved Brain Tumor Detection MRI Using Advanced Processing Techniques: Enhancement and Convolution Case Studies

Brain tumors present a significant challenge in medical imaging due to their complexity, requiring early detection and precise analysis for effective treatment. This study develops and evaluates advanced image processing workflows aimed at enhancing brain tumor image analysis. The proposed method involves four main steps: enlargement, pre-processing with min-max filters, enhancement, and convolution. The dataset used is from Kaggle, comprising 3,364 images categorized into Glioma (100 images), Meningioma (115 images), No Tumor (105 images), and Pituitary Tumor (74 images). For this study, images from the Glioma, Meningioma, and Pituitary Tumor categories were used, with one image selected from each category for technique evaluation. The results showed significant improvements in image clarity and detail, with high correlation values of 0.9851 for Meningioma and 0.9886 for Pituitary. These findings highlight the effectiveness of the proposed techniques in enhancing image quality and diagnostic accuracy.

Dual phase hierarchical brain tumour detection and segmentation using unet based skip guidance residual convolutional transformer

Brain tumour segmentation and classification is an important approach to understanding tumour characteristics effectively. Accurate lesion segmentation requires many image modalities with varied contrasts. As a result, manual segmentation may not be suitable for large-scale research. The research has shown interest in developing various learning algorithms to detect and segment brain tumour (BT) images accurately based on the set of experimental images. Some of the issues noticed in the existing models, such as high computational complexity, high processing time, and less accuracy, were identified. In order to overcome these existing issues, a novel Dual-phase channel attentional Residual convolutional transformer Unet model (DCARCTUnet) is introduced for segmenting brain tumours. Initially, the input images are passed into the pre-processing stage to remove noise and blur. The Efficient Net model identified the pre-processed image as either normal or tumour. The proposed segmentation model can be integrated into three stages, namely dual phase channel attention module (DCAM), residual convolutional transformer Unet model and Pyramid skip guidance module (PSM). The proposed method uses the BRATS 2020–2021 dataset to analyze the results accurately. The results showed that the proposed model has a dice coefficient value of 0.99 and a Jaccard coefficient value of 0.98. Furthermore, performance analysis is carried out to demonstrate the effectiveness of the proposed model.

Enhancing brain tumor classification through ensemble attention mechanism.

Brain tumors pose a serious threat to public health, impacting thousands of individuals directly or indirectly worldwide. Timely and accurate detection of these tumors is crucial for effective treatment and enhancing the quality of patients' lives. The widely used brain imaging technique is magnetic resonance imaging, the precise identification of brain tumors in MRI images is challenging due to the diverse anatomical structures. This paper introduces an innovative approach known as the ensemble attention mechanism to address this challenge. Initially, the approach uses two networks to extract intermediate- and final-level feature maps from MobileNetV3 and EfficientNetB7. This assists in gathering the relevant feature maps from the different models at different levels. Then, the technique incorporates a co-attention mechanism into the intermediate and final feature map levels on both networks and ensembles them. This directs attention to certain regions to extract global-level features at different levels. Ensemble of attentive feature maps enabling the precise detection of various feature patterns within brain tumor images at both model, local, and global levels. This leads to an improvement in the classification process. The proposed system was evaluated on the Figshare dataset and achieved an accuracy of 98.94%, and 98.48% for the BraTS 2019 dataset which is superior to other methods. Thus, it is robust and suitable for brain tumor detection in healthcare systems.

Deep bone oncology Diagnostics: Computed tomography based Machine learning for detection of bone tumors from breast cancer metastasis

PurposeThe objective of this study is to develop a novel diagnostic tool using deep learning and radiomics to distinguish bone tumors on CT images as metastases from breast cancer. By providing a more accurate and reliable method for identifying metastatic bone tumors, this approach aims to significantly improve clinical decision-making and patient management in the context of breast cancer. MethodsThis study utilized CT images of bone tumors from 178 patients, including 78 cases of breast cancer bone metastases and 100 cases of non-breast cancer bone metastases. The dataset was processed using the Medical Image Segmentation via Self-distilling TransUNet (MISSU) model for automated segmentation. Radiomics features were extracted from the segmented tumor regions using the Pyradiomics library, capturing various aspects of tumor phenotype. Feature selection was conducted using LASSO regression to identify the most predictive features. The model’s performance was evaluated using ten-fold cross-validation, with metrics including accuracy, sensitivity, specificity, and the Dice similarity coefficient. ResultsThe developed radiomics model using the SVM algorithm achieved high discriminatory power, with an AUC of 0.936 on the training set and 0.953 on the test set. The model’s performance metrics demonstrated strong accuracy, sensitivity, and specificity. Specifically, the accuracy was 0.864 for the training set and 0.853 for the test set. Sensitivity values were 0.838 and 0.789 for the training and test sets, respectively, while specificity values were 0.896 and 0.933 for the training and test sets, respectively. These results indicate that the SVM model effectively distinguishes between bone metastases originating from breast cancer and other origins. Additionally, the average Dice similarity coefficient for the automated segmentation was 0.915, demonstrating a high level of agreement with manual segmentations. ConclusionThis study demonstrates the potential of combining CT-based radiomics and deep learning for the accurate detection of bone metastases from breast cancer. The high-performance metrics indicate that this approach can significantly enhance diagnostic accuracy, aiding in early detection and improving patient outcomes. Future research should focus on validating these findings on larger datasets, integrating the model into clinical workflows, and exploring its use in personalized treatment planning.

Improved Unet brain tumor image segmentation based on GSConv module and ECA attention mechanism

In this paper, an improved model of medical image segmentation for brain tumor is discussed, which is a deep learning algorithm based on U-Net architecture. Based on the traditional U-Net, we introduce GSConv module and ECA attention mechanism to improve the performance of the model in medical image segmentation tasks. With these improvements, the new U-Net model is able to extract and utilize multi-scale features more efficiently while flexibly focusing on important channels, resulting in significantly improved segmentation results. During the experiment, the improved U-Net model is trained and evaluated systematically. By looking at the loss curves of the training set and the test set, we find that the loss values of both rapidly decline to the lowest point after the eighth epoch, and then gradually converge and stabilize. This shows that our model has good learning ability and generalization ability. In addition, by monitoring the change in the mean intersection ratio (mIoU), we can see that after the 35th epoch, the mIoU gradually approaches 0.8 and remains stable, which further validates the model. Compared with the traditional U-Net, the improved version based on GSConv module and ECA attention mechanism shows obvious advantages in segmentation effect. Especially in the processing of brain tumor image edges, the improved model can provide more accurate segmentation results. This achievement not only improves the accuracy of medical image analysis, but also provides more reliable technical support for clinical diagnosis. To sum up, the improved U-Net model based on GSConv module and ECA attention mechanism proposed in this paper provides a new solution for brain tumor medical image segmentation, and its superior performance helps to improve disease detection and treatment effects, which is of great significance in related fields. In the future, we hope to further explore the application potential of this method in other types of medical image processing to advance the development of medical imaging.

Deep learning-enabled fluorescence imaging for surgical guidance: in silico training for oral cancer depth quantification.

Oral cancer surgery requires accurate margin delineation to balance complete resection with post-operative functionality. Current in vivo fluorescence imaging systems provide two-dimensional margin assessment yet fail to quantify tumor depth prior to resection. Harnessing structured light in combination with deep learning (DL) may provide near real-time three-dimensional margin detection. A DL-enabled fluorescence spatial frequency domain imaging (SFDI) system trained with in silico tumor models was developed to quantify the depth of oral tumors. A convolutional neural network was designed to produce tumor depth and concentration maps from SFDI images. Three in silico representations of oral cancer lesions were developed to train the DL architecture: cylinders, spherical harmonics, and composite spherical harmonics (CSHs). Each model was validated with in silico SFDI images of patient-derived tongue tumors, and the CSH model was further validated with optical phantoms. The performance of the CSH model was superior when presented with patient-derived tumors ( ). The CSH model could predict depth and concentration within 0.4mm and , respectively, for in silico tumors with depths less than 10mm. A DL-enabled SFDI system trained with in silico CSH demonstrates promise in defining the deep margins of oral tumors.