Prognosis prediction of uterine cervical cancer using changes in the histogram and texture features of apparent diffusion coefficient during definitive chemoradiotherapy.

OBJECTIVES: We investigated prospectively whether, in cervical cancer (CC) treated with concurrent chemoradiotherapy (CCRT), the Apparent diffusion coefficient (ADC) histogram and texture parameters and their change rates during treatment could predict prognosis. METHODS: Fifty-seven CC patients treated with CCRT at our institution were included. They underwent MRI scans up to four times during the treatment course (1st, before treatment [n = 41], 2nd, at the start of image-guided brachytherapy (IGBT) [n = 41], 3rd, in the middle of IGBT [n = 27], 4th, after treatment [n = 53]). The entire tumor was manually set as the volume of interest (VOI) manually in the axial images of the ADC map by two radiologists. A total of 107 image features (morphology features 14, histogram features 18, texture features 75) were extracted from the VOI. The recurrence prediction values of the features and their change rates were evaluated by Receiver operating characteristics (ROC) analysis. The presence or absence of local and distant recurrence within two years was set as an outcome. The intraclass correlation coefficient (ICC) was also calculated. RESULTS: The change rates in kurtosis between the 1st and 3rd, and 1st and 2nd MRIs, and the change rate in grey level co-occurrence matrix_cluster shade between the 2nd and 3rd MRIs showed particularly high predictive powers (area under the ROC curve = 0.785, 0.759, and 0.750, respectively), which exceeded the predictive abilities of the parameters obtained from pre- or post-treatment MRI only. The change rate in kurtosis between the 1st and 2nd MRIs had good reliability (ICC = 0.765). CONCLUSIONS: The change rate in ADC kurtosis between the 1st and 2nd MRIs was the most reliable parameter, enabling us to predict prognosis early in the treatment course.

Impact of clinical information on CT diagnosis by radiologist and subsequent clinical management by physician in acute abdominal pain.

OBJECTIVE: The impact of clinical information on radiological diagnoses and subsequent clinical management has not been sufficiently investigated. This study aimed to compare diagnostic performance between radiological reports made with and without clinical information and to evaluate differences in the clinical management decisions based on each of these reports. METHODS: We retrospectively reviewed 410 patients who presented with acute abdominal pain and underwent unenhanced (n = 248) or enhanced CT (n = 162). Clinical information including age, sex, current and past history, physical findings, and laboratory tests were collected. Six radiologists independently interpreted CTs that were randomly assigned with or without clinical information, made radiological diagnoses, and scored the diagnostic confidence level. Four general and emergency physicians simulated clinical management (i.e., followed up in the outpatient clinic, hospitalized for conservative therapy, or referred to other departments for invasive therapy) based on reports made with or without the clinical information. Reference standards for the radiological diagnoses and clinical management were defined by an independent expert panel. RESULTS: The radiological diagnoses made with clinical information were more accurate than those made without clinical information (93.7% vs. 87.8%, p = 0.008). Median interpretation time for radiological reporting with clinical information was significantly shorter than that without clinical information (median 122.0 vs. 139.0 s, p < 0.001). Clinical simulation better matched the reference standard for clinical management when radiological diagnoses were made with reference to clinical information (97.3% vs. 87.8%, p < 0.001). CONCLUSION: Access to adequate clinical information enables accurate radiological diagnoses and appropriate subsequent clinical management of patients with acute abdominal pain. KEY POINTS: • Radiological interpretation improved diagnostic accuracy and confidence level when clinical information was provided. • Providing clinical information did not extend the interpretation time required by radiologists. • Radiological interpretation with clinical information led to correct clinical management by physicians.

Multidimensional Deep Learning Reduces False-Positives in the Automated Detection of Cerebral Aneurysms on Time-Of-Flight Magnetic Resonance Angiography: A Multi-Center Study.

Current deep learning-based cerebral aneurysm detection demonstrates high sensitivity, but produces numerous false-positives (FPs), which hampers clinical application of automated detection systems for time-of-flight magnetic resonance angiography. To reduce FPs while maintaining high sensitivity, we developed a multidimensional convolutional neural network (MD-CNN) designed to unite planar and stereoscopic information about aneurysms. This retrospective study enrolled time-of-flight magnetic resonance angiography images of cerebral aneurysms from three institutions from June 2006 to April 2019. In the internal test, 80% of the entire data set was used for model training and 20% for the test, while for the external tests, data from different pairs of the three institutions were used for training and the remaining one for testing. Images containing aneurysms > 15 mm and images without aneurysms were excluded. Three deep learning models [planar information-only (2D-CNN), stereoscopic information-only (3D-CNN), and multidimensional information (MD-CNN)] were trained to classify whether the voxels contained aneurysms, and they were evaluated on each test. The performance of each model was assessed using free-response operating characteristic curves. In total, 732 aneurysms (5.9 ± 2.5 mm) of 559 cases (327, 120, and 112 from institutes A, B, and C; 469 and 263 for 1.5T and 3.0T MRI) were included in this study. In the internal test, the highest sensitivities were 80.4, 87.4, and 82.5%, and the FPs were 6.1, 7.1, and 5.0 FPs/case at a fixed sensitivity of 80% for the 2D-CNN, 3D-CNN, and MD-CNN, respectively. In the external test, the highest sensitivities were 82.1, 86.5, and 89.1%, and 5.9, 7.4, and 4.2 FPs/cases for them, respectively. MD-CNN was a new approach to maintain sensitivity and reduce the FPs simultaneously.

A multi-scanner study of MRI radiomics in uterine cervical cancer: prediction of in-field tumor control after definitive radiotherapy based on a machine learning method including peritumoral regions.

PURPOSE: This study aimed to identify the most appropriate volume of interest (VOI) setting in prognostic prediction using pretreatment magnetic resonance imaging (MRI) radiomic analysis for cervical cancer (CC) treated with definitive radiotherapy. MATERIALS AND METHODS: The study participants were 87 patients who had undergone pretreatment MRI and definitive radiotherapy for CC. VOItumor was created with tumor alone and VOI+4 mm-VOI+20 mm mechanically expanded by 4-20 mm around each VOItumor in axial T2-weighted images (T2WI) and an apparent diffusion coefficient (ADC) map. A model was constructed to predict recurrence within the irradiation field within 2 years after treatment using imaging features from the VOI of each sequence. Sorting ability was evaluated by area under the receiver operator characteristic curve (AUC-ROC) analysis. RESULTS: VOI expansion improved AUC-ROCs compared with the predictive models of VOItumor (0.59 and 0.67 in T2WI and ADC, respectively). The AUC-ROCs of the models with imaging features from expanded VOI+4 mm in T2WI and VOI+4 mm and VOI+8 mm in ADC were 0.82, 0.82, and 0.86, respectively. CONCLUSION: Recurrence could be predicted with high accuracy using expanded VOI for CC treated with definitive radiotherapy, suggesting that including the pathological characteristics of invasive margins in radiomics may improve predictive ability.

Breast exposure reduction using organ-effective modulation on chest CT in Asian women.

PURPOSE: Organ-effective modulation (OEM) is a mechanism to reduce radiation dose to selected organs on computed tomography (CT). The purpose of this study was to measure radiation dose to the breast in Asian patients undergoing chest CT and to clarify the degree of exposure reduction. METHOD: We randomly selected 60 female patients undergoing non-contrast chest CT after breast cancer surgery. To measure radiation dose, an optically stimulated luminescence dosimeter had been attached directly to the gown over the nonoperated breast in 30 patients. Radiologists evaluated the image quality with and without OEM. In order to clarify the characteristics of OEM, the effects of angle and object size were measured using a phantom and an ionization chamber dosimeter. RESULTS: The OEM group received 9.1 ±â€¯1.9 mGy and the non-OEM group received 10.7 ±â€¯2.4 mGy. OEM reduced the exposure by 12.2% (P <  0.01). OEM caused no reduction in diagnostic quality. In the phantom study, the results of the angle effect were 3.2%, 11.2%, 28.7%, 31.3, 25.9%, 14.9% and 6.0% dose reductions at -90, -60, -30, 0, 30, 60 and 90°, respectively. The effect of the subject thickness was 3.7%, 17.5%, 30.2%, 31.7%, and 34.1% at 16, 20, 24, 28 and 32 cm diameters, respectively. CONCLUSIONS: OEM is a useful mechanism for reducing radiation exposure to the breast without affecting diagnostic imaging quality. The reduction rate correlated negatively with body habitus.