Abstract: There are provided a medical image processing device, an endoscope system, a diagnosis support device, and a medical service support device that can allow the observation of a medical image performed by a user not to be obstructed, allow a user not to miss a region of interest, and allow attention required during observation to be continued. An image acquisition unit acquires a medical image including a subject. A medical image is displayed in a first display region (A1) of a monitor. A bounding box, which is notification information, is superimposed and displayed on the medical image in the first display region (A1). In a case where the area of a region of interest is increased, or the like, the notification information is not displayed in the first display region (A1) and an icon, which is separate notification information, is displayed in a second display region (A2) of the monitor.

Abstract: Provided are an image processing device, an endoscope system, an image processing method, and a program capable of automatically differentiating a medical image including a scene of interest and supporting saving of the medical image according to a differentiation result.

Abstract: The system control unit functions as a captured image data acquisition unit that acquires captured image data obtained by imaging the inside of a subject with an endoscope; a visual-line detection unit 44B that detects a visual line directed to a display device that displays a captured image based on the captured image data; a processing unit that performs recognition processing for performing detection of a lesion site from the captured image data and identification of the detected lesion site on the captured image data; and a display control unit for causing the display device to display a result of the recognition processing by the processing unit. The processing unit controls the content of the recognition processing on the captured image data on the basis of the visual line detected by the visual-line detection unit.

Abstract: A medical image processing device having a processor configured to: acquire a medical image including an image of a subject; perform a first recognition of the medical image using a first recognizer; determine a confidence level for a recognition result of a first recognition by the first recognition; and perform a second recognition of the medical image using a second recognizer according to the confidence level for the recognition result of the first recognition, the second recognition having higher recognition accuracy than the first recognition.

Abstract: A medical image processing apparatus 10 includes a medical image acquisition unit 11 that acquires a medical image 50 including a subject image, a medical image analysis result acquisition unit 12 that acquires an analysis result obtained by analyzing the medical image 50, a display unit 13 that displays at least one medical image 50 and at least information on presence or absence of a lesion or a type of a lesion in the analysis result acquired by the medical image analysis result acquisition unit 12, and an input receiving unit 14 that receives an input regarding whether or not the information on presence or absence of a lesion or a type of a lesion included in the analysis result is correct.

Abstract: There are provided a medical image processing device, an endoscope system, a diagnosis support device, and a medical service support device that can allow the observation of a medical image performed by a user not to be obstructed, allow a user not to miss a region of interest, and allow attention required during observation to be continued. An image acquisition unit acquires a medical image including a subject. A medical image is displayed in a first display region (A1) of a monitor. A bounding box, which is notification information, is superimposed and displayed on the medical image in the first display region (A1). In a case where the area of a region of interest is increased, or the like, the notification information is not displayed in the first display region (A1) and an icon, which is separate notification information, is displayed in a second display region (A2) of the monitor.

Abstract: Provided are a medical image processing device, an endoscope system, and a method of operating a medical image processing device that can enhance the reliability for recognition results obtained by recognition processing in a case where a lesioned part or the like is diagnosed by recognition processing of artificial intelligence (AI). Comparison between a first medical image and a second medical image to be a comparison target with respect to the first medical image is performed. A specific medical image selected in accordance with a result of the comparison from among the second medical images is acquired. A monitor displays a plurality of recognition results that are obtained from recognition processing that is performed with respect to the specific medical image and performed for recognizing the observation target.

Abstract: An endoscope system comprises an image acquisition unit, a discrimination processing unit, and a discrimination processing control unit. The image acquisition unit acquires an endoscope image obtained by imaging an observation target using an endoscope. The discrimination processing unit discriminates a portion having a specific feature in the observation target by performing discrimination processing, using an endoscope image. The discrimination processing control unit controls a start or an end of the discrimination processing on the basis of a change in operation of an endoscope or the endoscope image.

Abstract: A wavelet transform, binary arithmetic coding and pass-by-pass partitioning of coded data streams according to JPEG 2000 are carried out and first and second layers for which the decoded image will have distortion ratios within a desired range are generated. If the total amount of code in the first layer is smaller than a target amount of code, then, from among coded data streams contained in the second layer, coded code up to a pass within a coded data stream having little influence upon image quality is added to the first layer. If the total amount of code in the first layer is greater than the target amount of code, then, from among coded data streams contained in the first layer, coded code within a coded data stream having little influence upon image quality is deleted from the first layer.

Abstract: A wavelet transform, binary arithmetic coding and pass-by-pass partitioning of coded data streams according to JPEG 2000 are carried out and first and second layers for which the decoded image will have distortion ratios within a desired range are generated. If the total amount of code in the first layer is smaller than a target amount of code, then, from among coded data streams contained in the second layer, coded code up to a pass within a coded data stream having little influence upon image quality is added to the first layer. If the total amount of code in the first layer is greater than the target amount of code, then, from among coded data streams contained in the first layer, coded code within a coded data stream having little influence upon image quality is deleted from the first layer.