Radiological Diagnosis Research Articles

Anterior thoracic myelomeningocele presenting with neck pain: an unusual spinal dysraphism

Cervicothoracic myelomeningocele is a rare entity with few cases reported in previous literature of anterior thoracic myelomeningocele. Spinal dysraphism (SD) is a congenital malformation of the spine involving the spinal cord which is characterized by incomplete midline closure of mesenchymal osseous and nervous tissue in the developing fetus. Early diagnosis of myelomeningoceles offers several benefits, including parental counselling, treatment planning, and reducing potential associated complications. MRI is the best modality to study soft tissue morphology of the cord as well as vertebral and discal pathologies. We report a case of 4-year-old female child presented with multiple episodes of neck pain of 1 year duration. The antenatal history was unremarkable except for lack of folic acid intake as a supplement during the pregnancy. There was mild kyphoscoliotic deformity in upper thoracic spine. Radiological imaging was done for further evaluation. MRI revealed herniation of a CSF containing thecal sac ventral to the spine protruding from D1 to D3 vertebral level through a midline defect with neural placode was seen within and tethering of the neural placode. On MRI, the radiological diagnosis of true anterior myelomeningocele was made. Congenital malformations of the spinal cord include a range of abnormalities with varying but distinctive imaging features thereby making MRI the best modality for evaluation and diagnosis. Radiologists and neurologists must both be aware of the wide spectrum of SD and the unusual presentations like neck pain or paraparesis, for early diagnosis and effective management. MRI of brain and spinal cord is the key in detection of anterior myelomenigocele which is an occult form of SD.

Controversies in the Application of AI in Radiology-Is There Medico-Legal Support? Aspects from Romanian Practice.

Background/Objectives: Artificial intelligence (AI) is gaining an increasing amount of influence in various fields, including medicine. In radiology, where diagnoses are based on collaboration between diagnostic devices and the professional experience of radiologists, AI intervention seems much easier than in other fields, but this is often not the case. Many times, the patients orient themselves according to the doctor, which is not applicable in the case of AI. Another limitation rests in the controversies regarding medico-legal liability. In the field of radio-imaging in Romania, the implementation of AI systems in diagnosis is at its beginning. An important aspect of this is raising awareness among the population about these assistive AI systems and, also, awareness of the technological evolution of AI among medical staff. This narrative review manuscript analyzes the existing literature data regarding the medico-legal aspects of AI application in radiology, highlighting the controversial aspects and the lack of statutory legislative regulations in Romania. Methods: A detailed search was conducted across three electronic databases including MEDLINE/PubMed, Scopus, and Web of Science, with 53 papers serving as the literature corpus of our review. Results: General requirements for artificial intelligence systems used in radiology have been established. In the radiological diagnostic process, there are five levels of AI system implication. Until now, completely autonomous AI systems have not been used. Regarding liability in the case of malpractice, at the currently accepted legislative level, most of the time, the radiologist is liable for their own fault or non-compliant use of diagnostic AI systems. Controversies arise in the case of radio-imaging diagnosis in which AI systems act autonomously. Conclusions: In order for AI diagnostic radio-imaging systems to be implemented, they must meet certain quality standards and be approved. The radiologist must know these systems, accept them, know their limits, and validate them in accordance with their degree of involvement in radiological diagnosis. Considering the evolution of technology in the Romanian medical system, including radiology, in the future, an alignment with the legal standards established/proposed at the European level is desired.

Characterization of the radiological markers in relation to the time elapsed between the appearance and the ventriculoperitoneal shunt placement.

This study was conducted to evaluate the time gap between earliest head CT with a significant Radscale score and ventriculo-peritoneal (VP) shunt placement. The study is a retrospective observational analytic study. The study population includes idiopathic normal pressure hydrocephalus (iNPH) patients treated with a VP shunt in a single center between the years 2016 and 2022 and have at least 2 CTs, one in proximity to diagnosis and another obtained at an earlier time point. The correlation among the parameters will be tested with statistical analysis software. 34 patients (mean age 72.32 years (SD ± 7.24), were evaluated. Based on the diagnostic CT among the Radscale parameters: 94.1% of patients had high Evans index score, 79.4% had enlarged sylvian fissures and 85.3% had enlargement of the temporal horns. 79.4% had normal structure of sulci. The median time duration between the earliest CT with a significant Radscale score and VP shunt placement was 9.2 months, interquartile range (IQR) 1.9 - 27.2 months. Evans index, enlarged sylvian fissures and enlargement of the temporal horns have been observed in the majority of diagnostic CTs. The median diagnosis time of iNPH since appearance of the radiological markers is 9.2 months, making the awareness and the communication between the referral and the radiologist crucial. Evaluation of the time gap between the appearance of the earliest radiological signs and clinical diagnosis of idiopathic normal pressure hydrocephalus.

Appendicectomy versus antibiotics for acute uncomplicated appendicitis in children: an open-label, international, multicentre, randomised, non-inferiority trial.

Support for the treatment of uncomplicated appendicitis with non-operative management rather than surgery has been increasing in the literature. We aimed to investigate whether treatment of uncomplicated appendicitis with antibiotics in children is inferior to appendicectomy by comparing failure rates for the two treatments. In this pragmatic, multicentre, parallel-group, unmasked, randomised, non-inferiority trial, children aged 5-16 years with suspected non-perforated appendicitis (based on clinical diagnosis with or without radiological diagnosis) were recruited from 11 children's hospitals in Canada, the USA, Finland, Sweden, and Singapore. Patients were randomly assigned (1:1) to the antibiotic or the appendicectomy group with an online stratified randomisation tool, with stratification by sex, institution, and duration of symptoms (≥48 h vs <48 h). The primary outcome was treatment failure within 1 year of random assignment. In the antibiotic group, failure was defined as removal of the appendix, and in the appendicectomy group, failure was defined as a normal appendix based on pathology. In both groups, failure was also defined as additional procedures related to appendicitis requiring general anaesthesia. Interim analysis was done to determine whether inferiority was to be declared at the halfway point. We used a non-inferiority design with a margin of 20%. All outcomes were assessed in participants with 12-month follow-up data. The trial was registered at ClinicalTrials.gov (NCT02687464). Between Jan 20, 2016, and Dec 3, 2021, 936 patients were enrolled and randomly assigned to appendicectomy (n=459) or antibiotics (n=477). At 12-month follow-up, primary outcome data were available for 846 (90%) patients. Treatment failure occurred in 153 (34%) of 452 patients in the antibiotic group, compared with 28 (7%) of 394 in the appendicectomy group (difference 26·7%, 90% CI 22·4-30·9). All but one patient meeting the definition for treatment failure with appendicectomy were those with negative appendicectomies. Of those who underwent appendicectomy in the antibiotic group, 13 (8%) had normal pathology. There were no deaths or serious adverse events in either group. The relative risk of having a mild-to-moderate adverse event in the antibiotic group compared with the appendicectomy group was 4·3 (95% CI 2·1-8·7; p<0·0001). Based on cumulative failure rates and a 20% non-inferiority margin, antibiotic management of non-perforated appendicitis was inferior to appendicectomy. None.

Lung Cancers Associated with Cystic Airspaces.

Lung cancer, the second most common malignancy in both men and women, poses a significant health burden. Early diagnosis remains pivotal in reducing lung cancer mortality. Given the escalating number of computed tomography (CT) examinations in both outpatient and inpatient settings, radiologists play a crucial role in identifying early-stage pulmonary cancers, particularly non-nodular cancers. Screening programs have been instituted to achieve this goal, and they have raised attention within the scientific community to lung cancers associated with cystic airspaces. These cancers, although they have been known for at least a decade, remain understudied. Limited investigations with small sample sizes have estimated their prevalence and explored their radiological and pathological features. Lung cancers associated with cystic airspaces exhibit varying complexities within their cystic components and demonstrate suspicious changes over time. Adenocarcinoma is the predominant histological type, often with a peripheral location. Differential diagnosis on CT scans includes inflammatory processes or emphysema-related changes. Unfortunately, prospective studies specifically analyzing the prevalence of cystic airspace-associated lung cancers are lacking. However, it is estimated that they constitute approximately one-fourth of delayed radiological diagnoses. Increased awareness among radiologists could lead to more timely identification and potentially reduce lung cancer mortality in a cost-effective manner.

Metastatic Alveolar Soft Part Sarcoma Presenting as an Adrenal Incidentaloma: A Case Report with Review of Literature.

Background. Metastasis of alveolar soft part sarcoma (ASPS) to the adrenal gland is infrequent, with only eight patients reported in the literature. Here we present an ASPS in an adolescent girl presented as a hypervascular adrenal incidentaloma along with a review of the available literature. This study aims to serve as a reference to aid in the pre-operative radiological and histopathological diagnosis of this rare entity. Case presentation. A 17-year-old adolescent girl presented to the Department of Urology after the detection of a hypervascular left adrenal incidentaloma on follow-up PET-CT, five months post-surgery for frontal bone ASPS. The radiological differential diagnoses were adrenocortical carcinoma, pheochromocytoma, and metastatic ASPS. The post-operative adrenalectomy specimen, on gross examination, revealed a solid, variegated tumor replacing the entire normal adrenal parenchyma. Haematoxylin and eosin-stained sections showed a tumor with cells dispersed in nests separated by large fibrovascular septae. The tumor cells were large, polygonal with abundant clear to eosinophilic cytoplasm and prominent nucleoli. Occasional mitotic figures, foci of necrosis, dystrophic calcification, and sinusoidal and vascular invasion were noted. Histopathological differential diagnoses were metastatic ASPS, a primary adrenocortical carcinoma, and local infiltration/metastases from renal cell carcinoma. Ancillary studies including immunohistochemistry, fluorescent in situ hybridization (FISH), and ultrastructural examination helped to confirm the diagnosis of alveolar soft part sarcoma metastatic to the adrenal gland. Conclusion. ASPS presenting as a hypervascular incidentaloma is rare and is likely to be misdiagnosed, especially as adrenocortical carcinoma, pheochromocytoma, and renal cell carcinoma. The differential diagnosis is further complicated by an overlap of pathological features among these entities. A relevant clinical history and ancillary tests are mandatory to diagnose these tumors. Early detection can help timely therapeutic intervention that can improve patient outcome.

Features of clinical, radiological and differential diagnosis of productive-destructive form of chronic osteomyelitis

Primary chronic osteomyelitis of the jaw bones is a rare and poorly studied pathology in the maxilofacial region, which causes difficulties in diagnosis, differential diagnosis and treatment. In this regard, the purpose of this study was to identify significant diagnostic and differential diagnostic clinical and radiological criteria in patients with productive-destructive form of chronic osteomyelitis of the jaw bones. 53 patients with chronic forms of osteomyelitis of the jaw bones were examined and treated. The main criteria that are important in the diagnosis of productive-destructive form of chronic osteomyelitis and comes as basis for planning comprehensive treatment were identified.

Features of clinical, radiological and differential diagnosis of productive-destructive form of chronic osteomyelitis

Issues of diagnosis, treatment, and medical rehabilitation of post-Covid syndrome in the maxillofacial area require further research. Complications after a COVID infection, which mainly affects the respiratory system, are numerous. Factors that determine the development of complications in the maxillofacial area are the virus itself, which leads to a hypercoagulability, and the drugs used in treatment, especially corticosteroids. Also significant are concomitant diseases, especially diabetes. Patients with severe purulent-necrotic lesions of the bones of the facial skull come to maxillofacial clinics.

OA-MEN: a fusion deep learning approach for enhanced accuracy in knee osteoarthritis detection and classification using X-Ray imaging.

Knee osteoarthritis (KOA) constitutes the prevailing manifestation of arthritis. Radiographs function as a common modality for primary screening; however, traditional X-ray evaluation of osteoarthritis confronts challenges such as reduced sensitivity, subjective interpretation, and heightened misdiagnosis rates. The objective of this investigation is to enhance the validation and optimization of accuracy and efficiency in KOA assessment by utilizing fusion deep learning techniques. This study aims to develop a highly accurate and lightweight model for automatically predicting and classifying KOA through knee X-ray imaging. We propose a deep learning model named OA-MEN, which integrates a hybrid model combining ResNet and MobileNet feature extraction with multi-scale feature fusion. This approach ensures enhanced extraction of semantic information without losing the advantages of large feature maps provided by high image resolution in lower layers of the network. This effectively expands the model's receptive field and strengthens its understanding capability. Additionally, we conducted unseen-data tests and compared our model with widely used baseline models to highlight its superiority over conventional approaches. The OA-MEN model demonstrated exceptional performance in tests. In the unseen-data test, our model achieved an average accuracy (ACC) of 84.88% and an Area Under the Curve (AUC) of 89.11%, marking improvements over the best-performing baseline models. These results showcase its improved capability in predicting KOA from X-ray images, making it a promising tool for assisting radiologists in diagnosis and treatment selection in clinical settings. Leveraging deep learning for osteoarthritis classification guarantees heightened efficiency and accuracy. The future goal is to seamlessly integrate deep learning and advanced computational techniques with the expertise of medical professionals.

Impact of Multimodal Prompt Elements on Diagnostic Performance of GPT-4V in Challenging Brain MRI Cases.

Background Studies have explored the application of multimodal large language models (LLMs) in radiologic differential diagnosis. Yet, how different multimodal input combinations affect diagnostic performance is not well understood. Purpose To evaluate the impact of varying multimodal input elements on the accuracy of OpenAI's GPT-4 with vision (GPT-4V)-based brain MRI differential diagnosis. Materials and Methods Sixty brain MRI cases with a challenging yet verified diagnosis were selected. Seven prompt groups with variations of four input elements (image without modifiers [I], annotation [A], medical history [H], and image description [D]) were defined. For each MRI case and prompt group, three identical queries were performed using an LLM-based search engine (Perplexity AI, powered by GPT-4V). The accuracy of LLM-generated differential diagnoses was rated using a binary and a numeric scoring system and analyzed using a χ2 test and a Kruskal-Wallis test. Results were corrected for false-discovery rate with use of the Benjamini-Hochberg procedure. Regression analyses were performed to determine the contribution of each input element to diagnostic performance. Results The prompt group containing I, A, H, and D as input exhibited the highest diagnostic accuracy (124 of 180 responses [69%]). Significant differences were observed between prompt groups that contained D among their inputs and those that did not. Unannotated (I) (four of 180 responses [2.2%]) or annotated radiologic images alone (I and A) (two of 180 responses [1.1%]) yielded very low diagnostic accuracy. Regression analyses confirmed a large positive effect of D on diagnostic accuracy (odds ratio [OR], 68.03; P < .001), as well as a moderate positive effect of H (OR, 4.18; P < .001). Conclusion The textual description of radiologic image findings was identified as the strongest contributor to the performance of GPT-4V in brain MRI differential diagnosis, followed by the medical history; unannotated or annotated images alone yielded very low diagnostic performance. © RSNA, 2025 Supplemental material is available for this article.

Medical thermal modeling and radiological diagnosis for disease prevention of AIDS patients: Rural survey intervention based on data mining in Baise City

Medical thermal modeling and radiological diagnosis for disease prevention of AIDS patients: Rural survey intervention based on data mining in Baise City

Advancements in Magnetic Resonance Imaging: Transforming Non-Invasive Diagnosis and Treatment Monitoring in Radiology

MRI is a crucial tool in radiology, enabling non-invasive diagnosis, disease staging, and treatment monitoring magnetic fields and radio waves. It produces detailed images by leveraging the magnetic properties of hydrogen atoms, allowing for precise anatomical insights without ionizing radiation. Techniques such as functional MRI (fMRI), diffusion-weighted imaging (DWI), and dynamic contrast-enhanced MRI (DCE-MRI) enhance tumor evaluation and understanding, aiding in the identification of high-risk patients and personalized treatments. MRI’s capabilities extend to imaging soft tissues, particularly beneficial for neurological diagnoses and research. Advanced methods provide insights into brain activity, tissue microstructure, and disease mechanisms, especially in cerebral small vessel disease (cSVD). Recent innovations, such as ultrahigh field MRI (7T), improve image resolution and facilitate the assessment of vascular health. These advancements enhance diagnostic accuracy and treatment strategies, ultimately improving patient outcomes.

The radiologic perspective of pulmonary tuberculosis seasonality in south-south Nigeria

Background: The periodic variation in the occurrence of disease within a calendar period is relatively common among many diseases, especially infectious diseases like tuberculosis (TB). Objective: The study is to radiologically evaluate the seasonality of pulmonary tuberculosis in our environment. Materials and Method: The study was a descriptive cross-sectional study over a period of 6 years (2017-2022) with one thousand, three hundred and fifty (1350) chest radiographs diagnosed of pulmonary tuberculosis. The chest radiographs were reviewed by three Radiologists with certification from the Faculty of Radiology of the West African College of Surgeons or the National Postgraduate Medical College of Nigeria. The data was analyzed descriptively using the statistical package for social science, SPSS version 23.0. Result: The monthly time series distribution of the radiologic diagnosis of pulmonary tuberculosis showed the lowest occurrences in the year 2020. The monthly average Seasonal Index of the radiologic occurrence of pulmonary TB shows that the months of June (1.29), July (1.95), and August (2.09) demonstrated the highest average seasonal index. The monthly averages from January to December over the 6 years of the study showed the highest occurrences in the month of August, and the lowest occurrences in the month of October. Conclusion: Although there were inconsistencies in the monthly pattern over the six year period, the highest incidence was in the month of August, followed by the month of July. Thus the study concludes that there exist seasonal variations in the radiologic diagnosis of pulmonary tuberculosis.

Scapholunate advanced collapse of the wrist: a review

Background. Scapholunate advanced collapse (SLAC) is a common type of the wrist osteoarthritis. It is characterized by progressive deformity, instability and arthritis due to chronic dissociation of the scaphoid and lunate bones with chronic scapholunate interosseous ligament (SLIL) injuries. Quite often, in this pathology, it is difficult to alleviate the pain syndrome and preserve the range of motion. The aim of the review — based on the modern literature data, to analyse the concept and pathogenesis of scapholunate advanced collapse, current methods of radiological diagnosis and treatment modalities of the pathology. Methods. The search was performed in eLIBRARY and PubMed databases using the following keywords: scapholunate advanced collapse, SLAC, scapholunate instability, proximal row carpectomy. We selected 86 original articles and reviews out of 110 papers found. The selected ones reveal the issues of pathogenesis, radiological diagnosis and treatment of the pathology. Results. Scapholunate carpal collapse is secondary arthritis of the carpal bones resulting from rupture of the SLIL, which can be traumatic or non-traumatic. Conservative methods of the SLAC treatment can be used in the early stage of arthritis, but there is no data on their effectiveness in the world literature. Surgical treatment methods are varied, the choice depends on the clinical stage of the disease. Conclusions. The efficiency of conservative treatment modalities of the SLAC syndrome has not been proved yet. There is a plenty of surgical treatment methods and their modifications developed to alleviate the pain syndrome and preserve the motion and strength of the wrist grip as far as it is possible. However, the choice of the treatment method depending on the clinical stage of the disease is still problematic. For young active patients especially important is the development of adjuvant techniques aimed to increase the treatment efficiency. To date, there is accumulating evidence of successful use of pyrocarbon implants and arthroscopy techniques in the wrist surgery.

Assessment of Symptom Burden and Quality of Life in Patients With Primary Brain Tumours Attending Palliative Care in a Tertiary Cancer Care Centre.

Background: Patients with primary brain tumors navigate a distinct illness trajectory, characterized by an uncertain prognosis, a rapid decline in physical functioning, and a significant deterioration in the quality of life. These unique challenges underscore the importance of our research in understanding and addressing the needs of these patients. Methods: The EORTC QLQ C30 & EORTC BN 20 questionnaires assessed the quality of life and symptom burden in patients with primary brain tumors. The scores were analyzed using SPSS statistical software. Results: 100 patients - 61 males and 39 females-were included with radiological or histopathological diagnoses of primary brain tumours. Seizures (38%) was the most common presenting symptom, followed by headache (18%), loss of consciousness (13%), focal neurological deficit (9%), and blurring of vision (8%). The mean quality of life at baseline was 78.29, with a standard deviation of 9.67 on a scale of 0 to 100, and the brain tumor-specific symptom burden score was 46.9, with a standard deviation of 17.95 on a scale of 0 to 100. There was a significant difference in the global health status score between the first and third visits at 3months (P value = .03). Conclusion: Despite the aggressive and often incurable nature of primary brain tumors, there is hope in the form of palliative care. By addressing unmet symptoms, uncertainties about the future, and social functioning, palliative care can significantly improve the quality of life of these patients.

Hydrodilatation: a comparison between diabetics and non-diabetics with adhesive capsulitis.

The primary aim of this retrospective study is to compare the short and medium-term outcomes for shoulder hydrodilatation for treatment of shoulder AC between diabetic and non-diabetic patients, to evaluate if there were better outcomes amongst non-diabetic patients. Patients with clinical or radiological diagnosis of AC and who underwent fluoroscopic guided shoulder hydrodilatation in our local institution from January 2021 to June 2022 were included in this study. Clinical outcomes were measured with visual analog scale (VAS) for pain and passive range of motion consisting of forward flexion (FF) and external rotation (ER) at pre-hydrodilatation, one month and six months post hydrodilatation. A total of 163 shoulders were included, corresponding to 156 patients consisting of 47 diabetics, 109 non-diabetics and seven bilateral shoulders (3 diabetics and 4 non-diabetics). At the time of presentation, there was no significant difference in VAS, FF or ER between diabetics and non-diabetics. From pre-hydrodilatation to 1-month post-hydrodilatation and one month to six months post-hydrodilatation, there was significant improvement in VAS, FF and ER for both groups. Comparing diabetics vs. non-diabetics, the non-diabetic group had significantly better FF (p < 0.01) at one month post hydrodilatation. At 6 months post-hydrodilatation, non-diabetic group also had significantly better outcomes including VAS score (p = 0.02), FF (p < 0.01) and ER (p = 0.02). Hydrodilatation is an effective treatment option in the short and medium term in both diabetics and non-diabetics with adhesive capsulitis, with good relief of pain and improvement in shoulder range of motion. Diabetic patients have significantly less improvement in range of motion and pain compared to non-diabetics at six months post hydrodilatation.

Enhancing Mammography Images with Artificial Intelligence to Improve Radiological Diagnosis in Breast Cancer

Breast cancer is one of the most common types of cancer in women, and early diagnosis is life-saving. The aim of this study is to enhance the resolution of mammography images, thereby improving the contrast resolution, spatial resolution, and the detectability of calcifications, distortions, and opacities in the images. For this purpose, mammography images obtained from the open-access mini-MIAS dataset were used. Both the original dataset and the images processed with the CLAHE (Contrast Limited Adaptive Histogram Equalization) algorithm underwent resolution enhancement using the Stable Diffusion artificial intelligence system. The results were evaluated by an expert radiologist, and it was determined that the diagnostic quality of the images significantly increased. These improvements aim to support early diagnosis in breast cancer and enhance diagnostic accuracy. Additionally, the applicability and effectiveness of these methods were emphasized, and the potential benefits of resolution enhancement techniques in clinical practice were discussed. The results have the potential to allow for more detailed and accurate analysis of mammography images, thereby improving patient care and treatment planning.

The acute management of Pilon fractures (ENFORCE) study: a national evaluation of practice.

Pilon fractures are potentially limb-threating injuries. Staged soft tissue damage control is described, but actual practices are unknown. We report a national trainee collaborative evaluating how tibial Pilon fractures are acutely managed. ENFORCE was a multicentre retrospective observational study of the acute management of tibial Pilon fractures over a three-year period. Mechanism of injury, imaging, fracture classification, time to cast application, soft tissue damage control strategy and definitive management details were determined. A total of 656 patients (670 fractures) across 27 centres were reported. AO fracture classifications were: partial articular (n=294) and complete articular (n=376). Initial diagnostic imaging mobilities were plain radiographs (n=602) and a trauma computed tomography (CT) scan (n=54). A total of 526 fractures had a cast applied in the emergency department (91 before radiological diagnosis), with the times taken to obtain postcast imaging being: mean 2.7 hours, median 2.3 hours and range 28 minutes-14 hours. 35% (102/294) of partial articular and 57% (216/376) of complete articular fractures had a spanning external fixator applied, all of which underwent a planning CT scan. Definitive management consisted of open reduction internal fixation (n=495), fine wire frame (n=86), spanning external fixator (n=25), intramedullary nail (n=25) or other (n=18). The management of tibial Pilon fractures is variable, with just over half of complete articular fractures managed with the gold standard 'span, scan, plan' staged soft tissue resuscitation. A national standard of care would increase the profile and standardise management of these potentially limb-threatening injuries, together with setting them apart from more straightforward ankle fractures.

What is Your Radiologic Diagnosis?

What is Your Radiologic Diagnosis?

Bullet Penetration In The Face Caused By Accidental Gunshot: A Case Report

Background: Clinical and radiological examinations are used to predict the location of the bullet in bullet penetration injury. The maxillofacial region had a variety of structure which could make the bullet deviate from its normal trajectories. Patient and Methods: A rare case of bullet penetration in the face caused by accidental gunshot is described. A 32 year-old male was hit by a bullet in the face with entrance wound on the left temporal region. Radiologic examination showed a bullet in the left inferior orbita. Treatment was exploration and extraction of the bullet. In this case we observe the difference between the clinical examination, radiological diagnosis and intraoperative findings Result: The patient underwent an explorative operation based on the prediction of location of the bullet from the clinical and radiological examination. The bullet was found in the inferior rectus muscle which the location is out of the prediction of clinical examination and radiologic findings. Summary: Clinical and radiological examination do not always give the accurate prediction regarding the location of bullet in penetrating bullet injury of the face because the face has a variety of bone, muscle and soft tissue structure.