Transition-zone PSA-density calculated from MRI deep learning prostate zonal segmentation model for prediction of clinically significant prostate cancer.

PURPOSE: To develop a deep learning (DL) zonal segmentation model of prostate MR from T2-weighted images and evaluate TZ-PSAD for prediction of the presence of csPCa (Gleason score of 7 or higher) compared to PSAD. METHODS: 1020 patients with a prostate MRI were randomly selected to develop a DL zonal segmentation model. Test dataset included 20 cases in which 2 radiologists manually segmented both the peripheral zone (PZ) and TZ. Pair-wise Dice index was calculated for each zone. For the prediction of csPCa using PSAD and TZ-PSAD, we used 3461 consecutive MRI exams performed in patients without a history of prostate cancer, with pathological confirmation and available PSA values, but not used in the development of the segmentation model as internal test set and 1460 MRI exams from PI-CAI challenge as external test set. PSAD and TZ-PSAD were calculated from the segmentation model output. The area under the receiver operating curve (AUC) was compared between PSAD and TZ-PSAD using univariate and multivariate analysis (adjusts age) with the DeLong test. RESULTS: Dice scores of the model against two radiologists were 0.87/0.87 and 0.74/0.72 for TZ and PZ, while those between the two radiologists were 0.88 for TZ and 0.75 for PZ. For the prediction of csPCa, the AUCs of TZPSAD were significantly higher than those of PSAD in both internal test set (univariate analysis, 0.75 vs. 0.73, p < 0.001; multivariate analysis, 0.80 vs. 0.78, p < 0.001) and external test set (univariate analysis, 0.76 vs. 0.74, p < 0.001; multivariate analysis, 0.77 vs. 0.75, p < 0.001 in external test set). CONCLUSION: DL model-derived zonal segmentation facilitates the practical measurement of TZ-PSAD and shows it to be a slightly better predictor of csPCa compared to the conventional PSAD. Use of TZ-PSAD may increase the sensitivity of detecting csPCa by 2-5% for a commonly used specificity level.

Natural language processing pipeline to extract prostate cancer-related information from clinical notes.

OBJECTIVES: To develop an automated pipeline for extracting prostate cancer-related information from clinical notes. MATERIALS AND METHODS: This retrospective study included 23,225 patients who underwent prostate MRI between 2017 and 2022. Cancer risk factors (family history of cancer and digital rectal exam findings), pre-MRI prostate pathology, and treatment history of prostate cancer were extracted from free-text clinical notes in English as binary or multi-class classification tasks. Any sentence containing pre-defined keywords was extracted from clinical notes within one year before the MRI. After manually creating sentence-level datasets with ground truth, Bidirectional Encoder Representations from Transformers (BERT)-based sentence-level models were fine-tuned using the extracted sentence as input and the category as output. The patient-level output was determined by compilation of multiple sentence-level outputs using tree-based models. Sentence-level classification performance was evaluated using the area under the receiver operating characteristic curve (AUC) on 15% of the sentence-level dataset (sentence-level test set). The patient-level classification performance was evaluated on the patient-level test set created by radiologists by reviewing the clinical notes of 603 patients. Accuracy and sensitivity were compared between the pipeline and radiologists. RESULTS: Sentence-level AUCs were ≥ 0.94. The pipeline showed higher patient-level sensitivity for extracting cancer risk factors (e.g., family history of prostate cancer, 96.5% vs. 77.9%, p < 0.001), but lower accuracy in classifying pre-MRI prostate pathology (92.5% vs. 95.9%, p = 0.002) and treatment history of prostate cancer (95.5% vs. 97.7%, p = 0.03) than radiologists, respectively. CONCLUSION: The proposed pipeline showed promising performance, especially for extracting cancer risk factors from patient's clinical notes. CLINICAL RELEVANCE STATEMENT: The natural language processing pipeline showed a higher sensitivity for extracting prostate cancer risk factors than radiologists and may help efficiently gather relevant text information when interpreting prostate MRI. KEY POINTS: When interpreting prostate MRI, it is necessary to extract prostate cancer-related information from clinical notes. This pipeline extracted the presence of prostate cancer risk factors with higher sensitivity than radiologists. Natural language processing may help radiologists efficiently gather relevant prostate cancer-related text information.

Cancer Detection Rate and Abnormal Interpretation Rate of Prostate MRI Performed for Clinical Suspicion of Prostate Cancer.

PURPOSE: To report cancer detection rate (CDR) and abnormal interpretation rate (AIR) in prostate MRI performed for clinical suspicion of prostate cancer (PCa). MATERIALS AND METHODS: This retrospective single-institution, three-center study included patients who underwent MRI for clinical suspicion of PCa between 2017 and 2021. Patients with known PCa were excluded. Patient-level Prostate Imaging-Reporting and Data System (PI-RADS) score was extracted from the radiology report. AIR was defined as number of abnormal MRI (PI-RADS score 3-5) / total number of MRIs. CDR was defined as number of clinically significant PCa (csPCa: Gleason score ≥7) detected at abnormal MRI / total number of MRI. AIR, CDR, and CDR adjusted for pathology confirmation rate were calculated for each of three centers and pre-MRI biopsy status (biopsy-naive and previous negative biopsy). RESULTS: A total of 9,686 examinations (8,643 unique patients) were included. AIR, CDR, and CDR adjusted for pathology confirmation rate were 45.4%, 23.8%, and 27.6% for center I; 47.2%, 20.0%, and 22.8% for center II; and 42.3%, 27.2%, and 30.1% for center III, respectively. Pathology confirmation rate ranged from 81.6% to 88.0% across three centers. AIR and CDR for biopsy-naive patients were 45.5% to 52.6% and 24.2% to 33.5% across three centers, respectively, and those for previous negative biopsy were 27.2% to 39.8% and 11.7% to 14.2% across three centers, respectively. CONCLUSION: We reported CDR and AIR in prostate MRI for clinical suspicion of PCa. CDR needs to be adjusted for pathology confirmation rate and pre-MRI biopsy status for interfacility comparison.

Cancer Detection Rate and Abnormal Interpretation Rate of Prostate MRI in Patients With Low-Grade Cancer.

PURPOSE: The aim of this study was to evaluate the utility of cancer detection rate (CDR) and abnormal interpretation rate (AIR) in prostate MRI for patients with low-grade prostate cancer (PCa). METHODS: This three-center retrospective study included patients who underwent prostate MRI from 2017 to 2021 with known low-grade PCa (Gleason score 6) without prior treatment. Patient-level highest Prostate Imaging Reporting & Data System (PI-RADS®) score and pathologic diagnosis within 1 year after MRI were used to evaluate the diagnostic performance of prostate MRI in detecting clinically significant PCa (csPCa; Gleason score ≥ 7). The metrics AIR, CDR, and CDR adjusted for pathologic confirmation rate were calculated. Radiologist-level AIR-CDR plots were shown. Simulation AIR-CDR lines were created to assess the effects of different diagnostic performances of prostate MRI and the prevalence of csPCa. RESULTS: A total of 3,207 examinations were interpreted by 33 radiologists. Overall AIR, CDR, and CDR adjusted for pathologic confirmation rate at PI-RADS 3 to 5 (PI-RADS 4 and 5) were 51.7% (36.5%), 22.1% (18.8%), and 30.7% (24.6%), respectively. Radiologist-level AIR and CDR at PI-RADS 3 to 5 (PI-RADS 4 and 5) were in the 36.8% to 75.6% (21.9%-57.5%) range and the 16.3%-28.7% (10.9%-26.5%) range, respectively. In the simulation, changing parameters of diagnostic performance or csPCa prevalence shifted the AIR-CDR line. CONCLUSIONS: The authors propose CDR and AIR as performance metrics in prostate MRI and report reference performance values in patients with known low-grade PCa. There was variability in radiologist-level AIR and CDR. Combined use of AIR and CDR could provide meaningful feedback for radiologists to improve their performance by showing relative performance to other radiologists.

Decreased prostate MRI cancer detection rate due to moderate to severe susceptibility artifacts from hip prosthesis.

OBJECTIVES: To evaluate the impact of susceptibility artifacts from hip prosthesis on cancer detection rate (CDR) in prostate MRI. MATERIALS AND METHODS: This three-center retrospective study included prostate MRI studies for patients without known prostate cancer between 2017 and 2021. Exams with hip prosthesis were searched on MRI reports. The degree of susceptibility artifact on diffusion-weighted images was retrospectively categorized into mild, moderate, and severe (> 66%, 33-66%, and < 33% of the prostate volume are evaluable) by blind reviewers. CDR was defined as the number of exams with Gleason score ≥7 detected by MRI (PI-RADS ≥3) divided by the total number of exams. For each artifact grade, control exams without hip prosthesis were matched (1:6 match), and CDR was compared. The degree of CDR reduction was evaluated with ratio, and influential factors were evaluated by expanding the equation. RESULTS: Hip arthroplasty was present in 548 (4.8%) of the 11,319 MRI exams. CDR of the cases and matched control exams for each artifact grade were as follows: mild (n = 238), 0.27 vs 0.25, CDR ratio = 1.09 [95% CI: 0.87-1.37]; moderate (n = 143), 0.18 vs 0.27, CDR ratio = 0.67 [95% CI: 0.46-0.96]; severe (n = 167), 0.22 vs 0.28, CDR ratio = 0.80 [95% CI: 0.59-1.08]. When moderate and severe artifact grades were combined, CDR ratio was 0.74 [95% CI: 0.58-0.93]. CDR reduction was mostly attributed to the increased frequency of PI-RADS 1-2. CONCLUSION: With moderate to severe susceptibility artifacts from hip prosthesis, CDR was decreased to 74% compared to the matched control. CLINICAL RELEVANCE STATEMENT: Moderate to severe susceptibility artifacts from hip prosthesis may cause a non-negligible CDR reduction in prostate MRI. Expanding indications for systematic prostate biopsy may be considered when PI-RADS 1-2 was assigned. KEY POINTS: • We proposed cancer detection rate as a diagnostic performance metric in prostate MRI. • With moderate to severe susceptibility artifacts secondary to hip arthroplasty, cancer detection rate decreased to 74% compared to the matched control. • Expanding indications for systematic prostate biopsy may be considered when PI-RADS 1-2 is assigned.

Artificial intelligence-powered software detected more than half of the liver metastases overlooked by radiologists on contrast-enhanced CT.

PURPOSE: To evaluate the sensitivity of artificial intelligence (AI)-powered software in detecting liver metastases, especially those overlooked by radiologists. METHODS: Records of 746 patients diagnosed with liver metastases (November 2010-September 2017) were reviewed. Images from when radiologists first diagnosed liver metastases were reviewed, and prior contrast-enhanced CT (CECT) images were checked for availability. Two abdominal radiologists classified the lesions into overlooked lesions (all metastases missed by radiologists on prior CECT) and detected lesions (all metastases if any of them were correctly identified and invisible on prior CECT or those with no prior CECT). Finally, images from 137 patients were identified, 68 of which were classified as "overlooked cases." The same radiologists created the ground truth for these lesions and compared them with the software's output at 2-month intervals. The primary endpoint was the sensitivity in detecting all liver lesion types, liver metastases, and liver metastases overlooked by radiologists. RESULTS: The software successfully processed images from 135 patients. The per-lesion sensitivity for all liver lesion types, liver metastases, and liver metastases overlooked by radiologists was 70.1%, 70.8%, and 55.0%, respectively. The software detected liver metastases in 92.7% and 53.7% of patients in detected and overlooked cases, respectively. The average number of false positives was 0.48 per patient. CONCLUSION: The AI-powered software detected more than half of liver metastases overlooked by radiologists while maintaining a relatively low number of false positives. Our results suggest the potential of AI-powered software in reducing the frequency of overlooked liver metastases when used in conjunction with the radiologists' clinical interpretation.

Severe TAFRO Syndrome Mimicking Hepatorenal Syndrome Successfully Treated with a Multidisciplinary Approach: A Case Report and Literature Review.

Finding the ideal balance between efficacy and safety of immunosuppression is challenging, particularly in cases of severe TAFRO syndrome. We herein report a 60-year-old man diagnosed with grade 5 TAFRO syndrome mimicking hepatorenal syndrome that was successfully treated by glucocorticoid, tocilizumab, and cyclosporin despite virus infection. Furthermore, by examining 14 peer-reviewed remission cases, we revealed that the recovery periods among inflammation, renal dysfunction, and thrombocytopenia were quite different, with recovery from thrombocytopenia notably slow. All patients requiring dialysis were successfully withdrawn from dialysis, and the reversibility from kidney injury was good. This clinical information will help clinicians plan treatments and tailor the intensity of immunosuppression.

A rare case of atypical ANCA-associated vasculitis without crescents overlapping with invasive pulmonary aspergillosis, successfully treated to remission with intravenous immunoglobulin therapy.

Antineutrophil cytoplasmic antibody (ANCA)-associated vasculitis (AAV) is life-threatening without treatment, but aggressive immunosuppression increases the risk of exacerbating a coexisting infection. Finding the balance between efficacy and safety of immunosuppression is challenging. We describe a 74-year-old man who was diagnosed with AAV following the aggravation of chronic pulmonary aspergillosis that required an aggressive antifungal agent. The laboratory data on admission demonstrated severe kidney failure requiring hemodialysis. Due to the active infection, we chose intravenous immunoglobulin (IVIg) as a low-risk initial treatment, which remarkably improved renal dysfunction (serum creatinine; 16.7 mg/dL-3.7 mg/dL) and systemic inflammation. Renal biopsy that was performed after renal recovery revealed atypical ANCA-associated nephritis without cellular crescents but with massive arteritis with multiple vascular sizes and diffuse interstitial inflammation. Despite these active AAV findings, adding plasma exchange therapy (PE) and low-dose steroids were sufficient to induce remission. The main pathogenesis of severe renal impairment was probably the reduction of blood flow, resulting from occlusions of small arteries by inflammatory cell infiltration and vascular endothelial injury due to AAV. Combination treatment with antifungal agents, IVIg, PE, and low-dose steroid treatment led to complete resolution of vasculitis. The specific histological findings and the good response to treatments suggest that pulmonary aspergillosis might trigger vasculitis through induction of ANCA antigen expression. IVIg could be an important option especially for cases of AAV associated with pulmonary aspergillosis.

Convolutional neural network for classifying primary liver cancer based on triple-phase CT and tumor marker information: a pilot study.

PURPOSE: To develop convolutional neural network (CNN) models for differentiating intrahepatic cholangiocarcinoma (ICC) from hepatocellular carcinoma (HCC) and predicting histopathological grade of HCC. MATERIALS AND METHODS: Preoperative computed tomography and tumor marker information of 617 primary liver cancer patients were retrospectively collected to develop CNN models categorizing tumors into three categories: moderately differentiated HCC (mHCC), poorly differentiated HCC (pHCC), and ICC, where the histopathological diagnoses were considered as ground truths. The models processed manually cropped tumor with and without tumor marker information (two-input and one-input models, respectively). Overall accuracy was assessed using a held-out dataset (10%). Area under the curve, sensitivity, and specificity for differentiating ICC from HCCs (mHCC + pHCC), and pHCC from mHCC were also evaluated. We assessed two radiologists' performance without tumor marker information as references (overall accuracy, sensitivity, and specificity). The two-input model was compared with the one-input model and radiologists using permutation tests. RESULTS: The overall accuracy was 0.61, 0.60, 0.55, 0.53 for the two-input model, one-input model, radiologist 1, and radiologist 2, respectively. For differentiating pHCC from mHCC, the two-input model showed significantly higher specificity than radiologist 1 (0.68 [95% confidence interval: 0.50-0.83] vs 0.45 [95% confidence interval: 0.27-0.63]; p = 0.04). CONCLUSION: Our CNN model with tumor marker information showed feasibility and potential for three-class classification within primary liver cancer.

Attribute-guided image generation of three-dimensional computed tomography images of lung nodules using a generative adversarial network.

PURPOSE: To develop and evaluate a three-dimensional (3D) generative model of computed tomography (CT) images of lung nodules using a generative adversarial network (GAN). To guide the GAN, lung nodule size was used. MATERIALS AND METHODS: A public CT dataset of lung nodules was used, from where 1182 lung nodules were obtained. Our proposed GAN model used masked 3D CT images and nodule size information to generate images. To evaluate the generated CT images, two radiologists visually evaluated whether the CT images with lung nodule were true or generated, and the diagnostic ability was evaluated using receiver-operating characteristic analysis and area under the curves (AUC). Then, two models for classifying nodule size into five categories were trained, one using the true and the other using the generated CT images of lung nodules. Using true CT images, the classification accuracy of the sizes of the true lung nodules was calculated for the two classification models. RESULTS: The sensitivity, specificity, and AUC of the two radiologists were respectively as follows: radiologist 1: 81.3%, 37.7%, and 0.592; radiologist 2: 77.1%, 30.2%, and 0.597. For categorization of nodule size, the mean accuracy of the classification model constructed with true CT images was 85% (range 83.2-86.1%), and that with generated CT images was 85% (range 82.2-88.1%). CONCLUSIONS: Our results show that it was possible to generate 3D CT images of lung nodules that could be used to construct a classification model of lung nodule size without true CT images.

Quantitative and Qualitative Evaluation of Convolutional Neural Networks with a Deeper U-Net for Sparse-View Computed Tomography Reconstruction.

RATIONALE AND OBJECTIVES: To evaluate the utility of a convolutional neural network (CNN) with an increased number of contracting and expanding paths of U-net for sparse-view CT reconstruction. MATERIALS AND METHODS: This study used 60 anonymized chest CT cases from a public database called "The Cancer Imaging Archive". Eight thousand images from 40 cases were used for training. Eight hundred and 80 images from another 20 cases were used for quantitative and qualitative evaluation, respectively. Sparse-view CT images subsampled by a factor of 20 were simulated, and two CNNs were trained to create denoised images from the sparse-view CT. A CNN based on U-net with residual learning with four contracting and expanding paths (the preceding CNN) was compared with another CNN with eight contracting and expanding paths (the proposed CNN) both quantitatively (peak signal to noise ratio, structural similarity index), and qualitatively (the scores given by two radiologists for anatomical visibility, artifact and noise, and overall image quality) using the Wilcoxon signed-rank test. Nodule and emphysema appearance were also evaluated qualitatively. RESULTS: The proposed CNN was significantly better than the preceding CNN both quantitatively and qualitatively (overall image quality interquartile range, 3.0-3.5 versus 1.0-1.0 reported from the preceding CNN; p < 0.001). However, only 2 of 22 cases used for emphysematous evaluation (2 CNNs for every 11 cases with emphysema) had an average score of ≥ 2 (on a 3 point scale). CONCLUSION: Increasing contracting and expanding paths may be useful for sparse-view CT reconstruction with CNN. However, poor reproducibility of emphysema appearance should also be noted.

Imaging Characteristics of Liver Metastases Overlooked at Contrast-Enhanced CT.

OBJECTIVE: The purpose of this study was to evaluate the imaging characteristics of liver metastases overlooked at contrast-enhanced CT. MATERIALS AND METHODS: The records of 746 patients with a diagnosis of liver metastases from colorectal, breast, gastric, or lung cancer between November 2010 and September 2017 were reviewed. Images were reviewed when liver metastases were first diagnosed, and images from prior contrast-enhanced CT examinations were checked if available. These lesions were classified into two groups: missed lesions (those missed on the prior images) and detected lesions (those correctly identified and invisible on the prior images or there were no prior images). Tumor size, contrast-to-noise ratio, location, presence of coexisting liver cysts and hepatic steatosis, and indications for examination were compared between the groups. The t test and Fisher exact test were used to analyze the imaging characteristics of previously overlooked lesions. RESULTS: The final analysis included 137 lesions, of which 68 were classified as missed. In univariate analysis, contrast-to-noise ratio was significantly lower in missed lesions (95% CI, 2.65 ± 0.24 vs 3.90 ± 0.23; p < 0.001). The proportion of subcapsular lesions (odds ratio, 3.44; p < 0.001), hepatic steatosis (odds ratio, 6.35; p = 0.007), and examination indication other than survey of malignant tumors (odds ratio, 9.07; p = 0.02) were significantly higher for missed lesions. CONCLUSION: Liver metastases without sufficient contrast enhancement, those in patients with hepatic steatosis, those in subcapsular locations, and those found at examinations for indications other than to assess for tumors were significantly more likely to be overlooked.