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.

Update on Percutaneous Ablation for Sarcoma.

PURPOSE OF REVIEW: To provide an update on the current state of percutaneous thermal ablation in the treatment of sarcoma. RECENT FINDINGS: Data continue to accrue in support of ablation for local control and palliation of specific sarcoma subtypes such as extra-abdominal desmoid fibromatosis and for broader indications such as the treatment of oligometastatic disease. The synergistic possibilities of various combination therapies such as cryoablation and immunotherapy represent intriguing areas of active investigation. Histotripsy is an emerging non-invasive, non-thermal ablative modality that may further expand the therapeutic arsenal for sarcoma treatment. Percutaneous thermal ablation is a valuable tool in the multidisciplinary management of sarcoma, offering a minimally invasive adjunct to surgery and radiation therapy. Although there remains a paucity of high-level evidence specific to sarcomas, ablation techniques are demonstrably safe and effective for achieving local tumor control and providing pain relief in select patients and are of particular benefit in those with metastatic disease or requiring palliative care.

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.

Safety and accuracy of aortic and periaortic CT-guided percutaneous core needle biopsy.

PURPOSE: The purpose of this study was to determine the safety and accuracy of aortic and periaortic computed tomography (CT)-guided percutaneous core needle biopsy performed at a single center over 12 years. MATERIALS AND METHODS: A retrospective review was conducted of cases performed between February 2010 and August 2022 in which the biopsied region was in direct contact with the aorta or great vessels including the pericardium and common iliac arteries. Clinical notes were reviewed for any early or delayed complications following the procedure, which if present were graded using the National Institute of Health's Common Terminology Criteria for Adverse Events, version 5.0. Pathology results were compared to subsequent outside biopsy results or follow-up surgical pathology, if available, as well as subsequent clinical decision making and/or clinical course, to determine concordance. Sensitivity, specificity, predictive value, and accuracy (indicative of diagnostic yield) were calculated. RESULTS: 32 core needle biopsies were reviewed from 30 patients (average lesion longest diameter 3.1 cm, range 0.5-10.9 cm; average needle proximity to the vessel endothelium or deep side of the pericardium 1.0 cm, range 0.3-1.8 cm). Complications occurred in 46.9% of cases (15/32), 93.3% (14/15) of which were minor and included small amounts of bleeding or pain. One patient developed a small nonemergent pneumothorax. Of biopsies obtained, 96.9% provided adequate tissue for diagnosis (31/32). When evaluating concordance between pathological and final diagnosis, sensitivity was 94.7% and specificity was 83.3%; positive and negative predictive value were 90.0% and 90.9%, respectively. Accuracy (diagnostic yield) of biopsy was 90.3%. CONCLUSION: CT-guided percutaneous aortic and periaortic core needle biopsies are safe and efficacious procedures with high diagnostic yield.

Impact of measurement method on interobserver variability of apparent diffusion coefficient of lesions in prostate MRI.

PURPOSE: To compare the inter-observer variability of apparent diffusion coefficient (ADC) values of prostate lesions measured by 2D-region of interest (ROI) with and without specific measurement instruction. METHODS: Forty lesions in 40 patients who underwent prostate MR followed by targeted prostate biopsy were evaluated. A multi-reader study (10 readers) was performed to assess the agreement of ADC values between 2D-ROI without specific instruction and 2D-ROI with specific instruction to place a 9-pixel size 2D-ROI covering the lowest ADC area. The computer script generated multiple overlapping 9-pixel 2D-ROIs within a 3D-ROI encompassing the entire lesion placed by a single reader. The lowest mean ADC values from each 2D-small-ROI were used as reference values. Inter-observer agreement was assessed using the Bland-Altman plot. Intraclass correlation coefficient (ICC) was assessed between ADC values measured by 10 readers and the computer-calculated reference values. RESULTS: Ten lesions were benign, 6 were Gleason score 6 prostate carcinoma (PCa), and 24 were clinically significant PCa. The mean±SD ADC reference value by 9-pixel-ROI was 733 ± 186 (10-6 mm2/s). The 95% limits of agreement of ADC values among readers were better with specific instruction (±112) than those without (±205). ICC between reader-measured ADC values and computer-calculated reference values ranged from 0.736-0.949 with specific instruction and 0.349-0.919 without specific instruction. CONCLUSION: Interobserver agreement of ADC values can be improved by indicating a measurement method (use of a specific ROI size covering the lowest ADC area).

Percutaneous MR Imaging-Guided Laser Ablation and Cryoablation for the Treatment of Pediatric and Adult Symptomatic Peripheral Soft Tissue Vascular Anomalies.

PURPOSE: To evaluate the safety and effectiveness of percutaneous magnetic resonance (MR) imaging-guided laser ablation and cryoablation for the treatment of symptomatic soft tissue vascular anomalies (VAs) of the trunk and extremities. MATERIALS AND METHODS: An institutional review board-approved retrospective review was undertaken of all pediatric and adult patients who underwent MR imaging-guided and monitored laser ablation and/or cryoablation for the treatment of symptomatic peripheral soft tissue VA. Preablation and postablation MR imaging was independently reviewed. Pain scores on the visual analog scale (0 to 10) and self-reported subjective symptomatic improvement were assessed. Change in VA size and pain scores were compared using a paired t test. RESULTS: Thirty patients (24 females; age, 10-75 years) with 34 VAs were treated for moderate to severe pain (n = 27) or swelling/mass effect (n = 3) with 60 total ablation sessions. The baseline maximum VA diameter was 9.5 cm ± 8.6. At baseline, all VAs (100%) demonstrated variable T2-weighted signal hyperintensity and enhancement. The baseline pain score was 6.4 ± 1.6. Clinical follow-up was available for 23 patients. At a mean follow-up time of 12.2 months ± 10.1, 19 of 20 (95%) patients treated for pain and 2 of 3 (67%) patients treated for swelling/mass effect reported partial or complete symptomatic relief. There was a significant decrease in the postablation pain scores (-5.7 ± 1.0, P < .001) and maximum VA size (-2.3 cm ± 2.7, P = .004), with >50% reduction in VA T2 signal (59%) and enhancement (73%). Nine of 30 (30%) patients experienced minor complications. CONCLUSIONS: MR imaging-guided and monitored percutaneous laser ablation and cryoablation appear to be safe and effective for the treatment of symptomatic peripheral soft tissue VAs.

Eccrine angiomatous hamartoma: First case in the cytology literature.

A 34-year-old male presented with a swelling on the volar surface of the third digit of his right hand. This swelling was associated with pain and erythema. Ultrasound-guided needle biopsy was performed. Cytologic and histologic preparations together confirmed the diagnosis of a rarely encountered mixed epithelial and mesenchymal proliferation, an eccrine angiomatous hamartoma. To our knowledge, this case is the first to illustrate the cytomorphologic features of this rare lesion.

Toolkit for young professionals: how to get involved in the society of abdominal radiology-workshops, disease focus panels, emerging technology committees, and more.

The Society of Abdominal Radiology (SAR) has grown rapidly in the last decade and with growth comes opportunity. The purpose of this article is to highlight the many potential ways in which early career radiologists (those within the first 7 years of their career) can become involved with the SAR, both at the annual meeting and throughout the year. At the annual meeting, there are opportunities for presentation of scientific sessions as well as submission of clinically oriented workshops. Workshops are a great way to develop presentation skills and highlight subspecialty clinical expertise. Disease focus panels (DFPs) and Emerging Technology Committees (ETCs) meet at the annual meeting but continue their work throughout the year, targeting improvements in clinical care and research. Finally, a variety of volunteer staffed committees are essential to the fulfillment of the mission of the SAR, and several of these are targeted at involving early career members, providing opportunities for leadership and exposure to other members of the society.

Implementation of peer learning conferences throughout a multi-site abdominal radiology practice.

PURPOSE: To initiate a peer learning conference for our abdominal radiology division across multiple geographically separated sites and different time zones, and to determine radiologist preference for peer learning versus traditional score-based peer review. METHODS: We implemented a monthly peer learning videoconference for our abdominal radiology division. Surveys regarding radiologist opinion regarding traditional peer review and the new peer learning conferences were conducted before and after 6 months of conferences. RESULTS: Peer learning conferences were well attended across our multiple sites, with an average of 43 participants per conference. Radiologist opinion regarding peer review was poor, with survey radiologists responding positively to only 1 out of 12 process questions. Opinion regarding peer learning was extremely favorable, with radiologists responding positively to 12 out of the same 12 process questions. After 6 months of peer learning conferences, 87.9% of surveyed radiologists wished to continue them in some fashion, and no one preferred to return to score-based peer review alone. CONCLUSION: We successfully implemented a peer learning conference for our abdominal radiology division spread out over multiple geographic sites. Our radiologists strongly preferred peer learning conferences over our traditional peer review system for quality control.

Acute appendiceal diverticulitis: a case report.

Acute appendiceal diverticulitis is a difficult prospective diagnosis due to both its rarity and clinical overlap with other ileocecal diseases, such as acute appendicitis. Few preoperative radiological images of acute appendiceal diverticulitis have been presented in the literature. We report a case of acute appendiceal diverticulitis initially diagnosed with outpatient ultrasound and confirmed with contrast-enhanced computed tomography in an 85-year-old male who presented with right lower quadrant pain. Appendiceal diverticulitis is an often overlooked diagnosis, and given its association with appendiceal neoplasms and relatively high rate of perforation, it is important to consider this entity in patients with right lower quadrant pain in order to ensure that they are managed appropriately. The addition of high quality ultrasound and computed tomography (CT) images to the literature may heighten awareness of this rare condition and facilitate accurate preoperative diagnosis and management in these patients.

Percutaneous Image-Guided Core Needle Biopsy of Neuroendocrine Tumors: How Common Is Intraprocedural Carcinoid Crisis?

PURPOSE: To retrospectively evaluate the incidence of carcinoid crisis, other complications, and physiologic disturbances during percutaneous image-guided core needle biopsy of neuroendocrine tumors (NETs) in the lung and the liver. MATERIALS AND METHODS: Between January 2010 and January 2020, 106 computed tomography (CT) or ultrasound (US)-guided core needle biopsies of lung and liver NETs were performed in 95 consecutive adult patients. The mean age was 64 ± 13 years, and 48% were female. The small bowel was the most common primary site (33%, 31/95), and 32 (34%) patients had pre-existing symptoms of carcinoid syndrome. The mean tumor size was 3.2 ± 2.6 cm, and mean number of passes was 3.4 ± 1.6. A 17/18-gauge needle was used in 91% (96/106) of the biopsies. Thirteen (12%) patients received either outpatient or prophylactic octreotide. RESULTS: No patients experienced carcinoid crisis or needed octreotide, inotropes, vasopressors, or resuscitation. A single biopsy procedure (0.9%, 1/106) was complicated by bleeding that required angiographic hepatic artery embolization. Changes in pre-biopsy- versus post-biopsy systolic blood pressure and heart rate were -1.6 mm Hg (P = .390) and 0.6 beat/min (P = .431), respectively. Tumor functional status, overall tumor burden, and the elevation of neuroendocrine markers were not associated with intraprocedural physiologic disturbances. There were 4 minor complications (0.4%, 4/106) associated with the biopsy procedure that were not attributed to hormone excretion from tumor manipulation. CONCLUSIONS: Percutaneous image-guided core biopsy of NETs is safe, with low complication rate and no definite carcinoid crisis in the current cohort.

Thoracic positron emission tomography: 18F-fluorodeoxyglucose and beyond.

Ongoing technologic and therapeutic advancements in medicine are now testing the limits of conventional anatomic imaging techniques. The ability to image physiology, rather than simply anatomy, is critical in the management of multiple disease processes, especially in oncology. Nuclear medicine has assumed a leading role in detecting, diagnosing, staging and assessing treatment response of various pathologic entities, and appears well positioned to do so into the future. When combined with computed tomography (CT) or magnetic resonance imaging (MRI), positron emission tomography (PET) has become the sine quo non technique of evaluating most solid tumors especially in the thorax. PET/CT serves as a key imaging modality in the initial evaluation of pulmonary nodules, often obviating the need for more invasive testing. PET/CT is essential to staging and restaging in bronchogenic carcinoma and offers key physiologic information with regard to treatment response. A more recent development, PET/MRI, shows promise in several specific lung cancer applications as well. Additional recent advancements in the field have allowed PET to expand beyond imaging with 18F-flurodeoxyglucose (FDG) alone, now with the ability to specifically image certain types of cell surface receptors. In the thorax this predominantly includes 68Ga-DOTATATE which targets the somatostatin receptors abundantly expressed in neuroendocrine tumors, including bronchial carcinoid. This receptor targeted imaging technique permits targeting these tumors with therapeutic analogues such as 177Lu labeled DOTATATE. Overall, the proper utilization of PET in the thorax has the ability to directly impact and improve patient care.

Malabsorption Syndromes, Vasculitis, and Other Uncommon Diseases.

MR enterography is frequently ordered for patients with suspected small bowel disorders. In this article, disease-causing malabsorption, vasculitides, and some of the less common small bowel diseases are reviewed. The clinical presentations, diagnostic criteria, and imaging findings of these diseases are discussed. Because the imaging findings in several small bowel diseases are nonspecific and/or overlap, radiologists must correlate clinical data with imaging to develop a narrower differential diagnosis. The unique or characteristic findings in certain diseases are also emphasized.

Multimodal Imaging Aids in the Diagnosis of Perineural Spread of Prostate Cancer.

BACKGROUND: The perineural spread of prostate cancer into pelvic peripheral nerves is a rare, but increasingly recognized, entity. This form of metastasis invades the lumbosacral plexus via the splanchnic nerves innervating the prostate. The prevalence of perineural spread is likely underappreciated, and further imaging-based studies are needed to elucidate its true frequency. METHODS: A retrospective review was performed using an institutional radiology database. Medical reports from patients with prostate cancer who had undergone positron emission tomography (PET) imaging were queried for terms suggestive of perineural spread. PET and magnetic resonance imaging (MRI) from the identified patients were blindly reviewed for peripheral nerve involvement by 2 nuclear medicine and 2 musculoskeletal radiologists. RESULTS: A total of 22 patients were identified. After review by the radiologists, 16 patients had positive findings of perineural spread found on PET and 15 had abnormalities found on MRI involving lumbosacral plexus neural elements. All patients with biopsy-proven neoplastic perineural spread (including 1 patient with malignant peripheral nerve sheath tumor) had positive findings on both PET and MRI. All patients with biopsy-proven inflammatory lesions had negative PET and variable MRI findings. CONCLUSIONS: The perineural spread of prostate cancer might be more common than previously thought. The use of multimodal imaging for patients suspected of having perineural spread should be a part of the treatment algorithm. Targeted fascicular biopsy might be indicated for patients with progressive neurological deficit and an unclear diagnosis.

Sensory versus cognitive components in harmonic priming.

This study investigated the strength of sensory and cognitive components involved in musical priming. In Experiment 1, the harmonic function of the target chord and the number of pitch classes shared by the prime sequence and the target chord were manipulated. In Experiment 2, the temporal course of sensory and cognitive priming was investigated. For both musician and nonmusician listeners, cognitive priming systematically overruled sensory priming even at fast and very fast tempi (300 ms and 150 ms per chord). Cognitive priming continued to challenge sensory priming processes at extremely fast tempo (75 ms per chord) but only for participants who began the experimental session with slower tempi. This outcome suggests that the cognitive component is a fast-acting component that competes with sensory priming.