Deep learning-based radiomic nomograms for predicting Ki67 expression in prostate cancer.

BACKGROUND: To explore the value of a multiparametric magnetic resonance imaging (MRI)-based deep learning model for the preoperative prediction of Ki67 expression in prostate cancer (PCa). MATERIALS: The data of 229 patients with PCa from two centers were retrospectively analyzed and divided into training, internal validation, and external validation sets. Deep learning features were extracted and selected from each patient's prostate multiparametric MRI (diffusion-weighted imaging, T2-weighted imaging, and contrast-enhanced T1-weighted imaging sequences) data to establish a deep radiomic signature and construct models for the preoperative prediction of Ki67 expression. Independent predictive risk factors were identified and incorporated into a clinical model, and the clinical and deep learning models were combined to obtain a joint model. The predictive performance of multiple deep-learning models was then evaluated. RESULTS: Seven prediction models were constructed: one clinical model, three deep learning models (the DLRS-Resnet, DLRS-Inception, and DLRS-Densenet models), and three joint models (the Nomogram-Resnet, Nomogram-Inception, and Nomogram-Densenet models). The areas under the curve (AUCs) of the clinical model in the testing, internal validation, and external validation sets were 0.794, 0.711, and 0.75, respectively. The AUCs of the deep models and joint models ranged from 0.939 to 0.993. The DeLong test revealed that the predictive performance of the deep learning models and the joint models was superior to that of the clinical model (p < 0.01). The predictive performance of the DLRS-Resnet model was inferior to that of the Nomogram-Resnet model (p < 0.01), whereas the predictive performance of the remaining deep learning models and joint models did not differ significantly. CONCLUSION: The multiple easy-to-use deep learning-based models for predicting Ki67 expression in PCa developed in this study can help physicians obtain more detailed prognostic data before a patient undergoes surgery.

Can DWI provide additional value to Kaiser score in evaluation of breast lesions.

OBJECTIVES: To explore added value of diffusion-weighted imaging (DWI) as an adjunct to Kaiser score (KS) for differentiation of benign from malignant lesions on breast magnetic resonance imaging (MRI). METHODS: Two hundred forty-six patients with 273 lesions (155 malignancies) were included in this retrospective study from January 2015 to December 2019. All lesions were proved by pathology. Two radiologists blind to pathological results evaluated lesions according to KS. Lesions with score > 4 were considered malignant. Four thresholds of ADC values -1.3 × 10-3mm2/s, 1.4 × 10-3mm2/s, 1.53 × 10-3mm2/s, and 1.6 × 10-3mm2/s were used to distinguish benign from malignant lesions. For combined diagnosis, a lesion with KS > 4 and ADC values below the preset cutoffs was considered as malignant; otherwise, it was benign. Sensitivity, specificity, and area under the curve (AUC) were compared between KS, DWI, and combined diagnosis. RESULTS: The AUC of KS was significantly higher than that of DWI alone (0.941 vs 0.901, p = 0.04). The sensitivity of KS (96.8%) and DWI (97.4 - 99.4%) was comparable (p > 0.05) while the specificity of KS (83.9%) was significantly higher than that of DWI (19.5-56.8%) (p < 0.05). Adding DWI as an adjunct to KS resulted in a 0-2.5% increase of specificity and a 0.1-1.3% decrease of sensitivity; however, the difference did not reach statistical significance (p > 0.05). CONCLUSION: KS showed higher diagnostic performance than DWI alone for discrimination of breast benign and malignant lesions. DWI showed no additional value to KS for characterizing breast lesions. KEY POINTS: • KS showed higher diagnostic performance than DWI alone for differentiation of benign from breast malignant lesions. • DWI alone showed a high sensitivity but a low specificity for characterizing breast lesions. • Diagnostic performance did not improve using DWI as an adjunct to KS.

Intrinsic brain abnormalities of irritable bowel syndrome with diarrhea: a preliminary resting-state functional magnetic resonance imaging study.

BACKGROUND: The aim of the present study was to explore the brain active characteristics of patients with irritable bowel syndrome with diarrhea (IBS-D) using resting-state functional magnetic resonance imaging technology. METHODS: Thirteen IBS-D patients and fourteen healthy controls (HC) were enrolled. All subjects underwent head MRI examination during resting state. A voxel-based analysis of fractional amplitude of low frequency fluctuation (fALFF) maps between IBS-D and HC was performed using a two-sample t-test. The relationship between the fALFF values in abnormal brain regions and the scores of Symptom Severity Scale (IBS-SSS) were analyzed using Pearson correlation analysis. RESULTS: Compared with HC, IBS-D patients had lower fALFF values in the left medial superior frontal gyrus and higher fALFF values in the left hippocampus and right precuneus. There was a positive correlation between the duration scores of IBS-SSS and fALFF values in the right precuneus. CONCLUSION: The altered fALFF values in the medial superior frontal gyri, left hippocampus and right precuneus revealed changes of intrinsic neuronal activity, further revealing the abnormality of gut-brain axis of IBS-D.

Primary hepatic melanoma: A case report of computed tomography and magnetic resonance imaging findings.

RATIONALE: Malignant melanoma predominantly develops in middle-aged and older adults, most commonly occurring on the skin and rarely on internal organs. Malignant melanoma originating in the liver is extremely rare. Imaging findings of primary hepatic melanoma (PHM) are scarce in relevant literature. PATIENT CONCERNS: The patient was a 69-year-old woman from Zhejiang, China, who was admitted to the hospital because of upper abdominal pain that persisted for >10 days. DIAGNOSES: Computed tomography (CT) findings indicated the presence of a circular low-density shadow of approximately 7.5 × 8.0 cm in the hepatic hilar region. Magnetic resonance imaging (MRI) indicated a heterogeneous solid cystic mass in the hepatic hilar region. The mass exhibited heterogeneous low-signal intensity on a T1-weighted image (T1WI) and slightly higher signal intensity on a T2-weighted image (T2WI). The tumor appeared as multiple irregular strips with high-signal intensity on T1WI and low-signal intensity on T2WI. The diffusion-weighted image revealed increased signal intensity. The tumor continued to be enhanced after enhancement. Clinical data suggested that the tumor was a malignant liver tumor. INTERVENTIONS: The patient underwent a CT guide puncture hepatic biopsy. The tumor was located in the hepatic hilar region adjacent to the large blood vessels and invaded the portal vein. Because a resection was highly risky, conservative treatment was conducted. OUTCOMES: Postoperative pathology and clinical examination confirmed that the tumor was malignant PHM. The patient has been followed up for 6 months. The patient underwent CT reexamination 2 months after conservative treatment, the results of which revealed that the tumor progressed. Multiple lesions were identified; moreover, the tumor size had increased and the tumor had invaded the portal vein and intrahepatic bile duct. The patient was reexamined by CT in another hospital 6 months after conservative treatment. The results revealed peritoneal, omental metastases and multi bone metastases. LESSONS: To our best knowledge, this is the first reported case of a PHM with complete imaging data, including preoperative CT and MRI examinations and a follow-up CT examination. From compiling the CT and MRI findings of this patient and those of relevant studies, this study can serve as a reference for the preoperative diagnosis and differential diagnosis of PHM.

A pilot study of radiomics technology based on X-ray mammography in patients with triple-negative breast cancer.

PURPOSE: To explore the radiomics features of triple negative breast cancer (TNBC) and non-triple negative breast cancer (non-TNBC) based on X-ray mammography, and to differentiate the two groups of cases. MATERIALS AND METHODS: Preoperative mammograms of 120 patients with breast ductal carcinoma confirmed by surgical pathology were retrospectively analyzed, which include 30 TNBC and 90 non-TNBC patients. The manual segmentation of breast lesions was performed by ITK-SNAP software and 12 radiomics features were extracted by Omni-Kinetics software. The differences of these radiomics features between TNBC and non-TNBC groups were compared, and the receiver operating characteristic (ROC) curve was used to determine the optimal cutoff value of each radiomics parameter for differentiating TNBC from non-TNBC, and the corresponding area under the curve (AUC), sensitivity and specificity were obtained. RESULTS: There were statistically significant differences for 4 radiomics features between TNBC and non-TNBC datasets (P < 0.05). They were the roundness, concavity, gray average and skewness of breast lesions. Compared with non-TNBC, TNBC cases have following characteristics of (1) more round with the roundness of 0.621 vs. 0.413 (P < 0.001), (2) more regular with the concavity of 0.087 vs. 0.141 (P < 0.01), (3) higher density or gray average (67.261 vs. 56.842, P < 0.05), and (4) lower skewness (- 0.837 vs.- 0.671, P = 0.034). AUCs of ROC curves computed using features of the roundness and concavity were both larger than 0.70. CONCLUSION: Radiomics features based on X-ray mammography may be helpful to distinguish between TNBC and non-TNBC, which were associated with breast tumor histology.

Primary hyperparathyroidism characterized by diffuse homogeneous metastatic pulmonary calcification: A case report.

RATIONALE: Primary hyperparathyroidism (PHPTI) with respiratory tract symptom is extremely rare. It is caused by autonomic oversecretion of parathyroid hormone (PTH) owing to parathyroid adenoma, hyperplasia, or tumor. The diagnosis of PHPTI often needs to be made based on medical history, clinical manifestation, laboratory tests, and imaging examination. Moreover, no study has reported PHPTI with diffuse metastatic pulmonary calcification (MPC) as the characteristic. PATIENT CONCERNS: A 49-year-old female from Zhejiang, China, had a fever of unknown origin, cough with white crude sputum, and asthma after activity for 1 month. DIAGNOSIS: The computed tomography (CT) examination revealed a homogeneous and diffuse high-density shadow in both lungs. The pathologic examination with CT-guided lung biopsy (left lung puncture) suggested interstitial inflammation of the lung tissue, combined with fibroblast proliferation as well as calcification. B-ultrasonography identified a lump in the right parathyroid gland, with a size of 4.1 × 1.7 × 1.9 cm. Color Doppler sonography indicated rich blood flow inside the lump. Whole-body bone emission computed tomography imaging showed the enhancement of bone metabolism in bilateral lower extremities and a diffuse enhancement of radioactive distribution in both lungs. Tc-methoxyisobutyl isonitrile imaging suggested significantly increased MIBI uptake in the right superior pole of the thyroid gland and indicated adenoma of the right superior parathyroid. The diagnosis of PHPTI was confirmed by postoperative pathology. INTERVENTIONS: The patient received a resection of the right parathyroid adenoma. OUTCOMES: After surgery, the symptom such as fever, coughing, and white crude sputum were significantly alleviated. LESSONS: This novel case reported the case of a patient with PHPTI having respiratory tract infection as the 1st symptom and diffuse MPC as the symptom characteristic PHPTI, the findings of this case study might improve the recognition of PHPTI on diffuse pulmonary calcification for clinical doctors.

An application study of low-dose computed tomography perfusion imaging (LDCTPI) in breast cancer and breast fibroadenoma.

PURPOSE: To explore the characteristics of breast cancer and breast fibroadenoma using low-dose computed tomography perfusion imaging (LDCTPI) including specific perfusion parameter values, and seek the potential clinical applications in cancer prognosis assessment. MATERIALS AND METHODS: Fifty patients including 30 diagnosed with breast cancer and 20 with breast fibroadenoma, as well as 15 control subjects with normal breasts were studied prospectively using LDCTPI examinations. The acquired volumetric imaging data were used for calculation, mapping and analysis by using a body tumor perfusion protocol in the CT perfusion software to measure 4 parameters: blood flow (BF), blood volume (BV), mean transit time (MTT), and the permeability surface (PS) area product. Statistical data analysis was then performed to distinguish the difference of the 4 parameter values among normal control, breast cancer and breast fibroadenoma cases. RESULTS: The mean perfusion values of 15 normal controls were as follows: BF, 20.03±4.08 mL/100 g/min; BV, 4.53±0.95 mL/100 g; MTT, 5.90±0.82 s; and PS, 9.25±1.18 mL/100 g/min. The mean perfusion values of 30 cancer patients were as follows: BF, 56.67±6.59 mL/100 g/min; BV, 5.82±0.68 mL/100 g; MTT, 6.01±0.82 s; and PS, 24.95±5.05 mL/100 g/min. The mean perfusion values of 20 patients with breast fibroadenoma were as follows: BF, 46.24±6.65 mL/100 g/min; BV, 5.07±0.73 mL/100 g; MTT, 7.51±0.62 s; and PS, 16.73±6.48 mL/100 g/min. Comparing the 3 groups, differences were all statistically significant for BF, BV, MTT and PS values (p < 0.05, respectively); The BF, BV, PS values were highest in group of cancer patients, while the MTT value was highest in group of patients diagnosed with breast fibroadenoma. CONCLUSION: Breast CT perfusion imaging is a promising functional imaging technology in breast cancer diagnosis, which can provide valuable quantitative imaging markers to assist evaluation of breast tumors.

Magnetic resonance imaging DTI-FT study on schizophrenic patients with typical negative first symptoms.

Magnetic resonance imaging (MRI) with diffusion-tensor imaging (DTI) together with a white matter fiber tracking (FT) technique was used to assess different brain white matter structures and functionalities in schizophrenic patients with typical first negative symptoms. In total, 30 schizophrenic patients with typical first negative symptoms, comprising an observation group were paired 1:1 according to gender, age, right-handedness, and education, with 30 healthy individuals in a control group. Individuals in each group underwent routine MRI and DTI examination of the brain, and diffusion-tensor tractography (DTT) data were obtained through whole brain analysis based on voxel and tractography. The results were expressed by fractional anisotropy (FA) values. The schizophrenic patients were evaluated using a positive and negative symptom scale (PANSS) as well as a Global Assessment Scale (GAS). The results of the study showed that routine MRIs identified no differences between the two groups. However, compared with the control group, the FA values obtained by DTT from the deep left prefrontal cortex, the right deep temporal lobe, the white matter of the inferior frontal gyrus and part of the corpus callosum were significantly lower in the observation group (P<0.05). The PANSS positive scale value in the observation group averaged 7.7±1.5, and the negative scale averaged 46.6±5.9, while the general psychopathology scale averaged 65.4±10.3, and GAS averaged 53.8±19.2. The Pearson statistical analysis, the left deep prefrontal cortex, the right deep temporal lobe, the white matter of the inferior frontal gyrus and the FA value of part of the corpus callosum in the observation group was negatively correlated with the negative scale (P<0.05), and positively correlated with GAS (P<0.05). In conclusion, a decrease in the FA values of the left deep prefrontal cortex, the right deep temporal lobe, the white matter of the inferior frontal gyrus and part of the corpus callosum may be associated with schizophrenia with typical first negative symptoms and the application of MRI DTI-FT can improve diagnostic accuracy.

Multiple nodular lesions in spleen associated with visceral leishmaniasis: a case report of MRI-findings.

The spleen is one of the most commonly involved organs of visceral leishmaniasis (VL). However, there were few reports about imaging findings of splenic leishmaniasis, especially regarding MRI findings. This case report describes a 45 years old male patient from Zhejiang province of southeastern China, who was admitted for persistent fever of unknown origin, with splenomegaly and multiple hypodense/low echo nodules on CT/ultrasonography (USG) studies. MRI showed multiple nodules with concentric rings in the spleen on T2-weighted imaging (T2WI), with no obvious diffusion restriction on diffusion weighted imaging (DWI), and gradual ring-like enhancement after intravenous administration of contrast medium. So MRI suggested necrotic granulomatous lesion. By reviewing the clinical history and following positive serological leishmania antibody test, the patient was finally confirmed a recent infection with VL. The patient received antimony gluconate therapy intravenously. At 4 months follow-up, the contrast-enhanced abdominal MRI showed that the size of the spleen was returned to normal and the splenic lesions were completely resolved except for reduced infarction compared with the previous MRI. This is the first case which was performed MRI examination completely. Meanwhile, it is the second case which MRI findings were reported. As for the characteristics of MRI in this case, there are several features, which are helpful for giving the diagnosis and differential diagnosis of VL.